© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 126890
    Prev
    Next
    INDEX
    Explanations

    patients

    np_max-act · gemini-2.0-flash

    The neuron lights up for named entities and salient content words—proper nouns, acronyms, and important topic-specific nouns.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parity
    -0.08
    istinguished
    -0.07
    $tmp
    -0.07
    ATRIX
    -0.07
    (namespace
    -0.07
     besides
    -0.07
     ...)↵
    -0.07
    substr
    -0.07
    hover
    -0.07
    [${
    -0.07
    POSITIVE LOGITS
    얽
    0.08
     whiskey
    0.07
    �
    0.07
    סביב
    0.07
    흝
    0.07
    殖民
    0.06
    安置
    0.06
    ≀
    0.06
    🤕
    0.06
    携程
    0.06
    Activations Density 0.423%

    No Known Activations