© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 19-RESID-POST-AA
    11. 71063
    Prev
    Next
    INDEX
    Explanations

    credit

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    临床
    -0.07
     particular
    -0.07
    ��
    -0.07
    obsolete
    -0.07
     Nadu
    -0.06
    -fluid
    -0.06
    York
    -0.06
    .Margin
    -0.06
     replace
    -0.06
    gar
    -0.06
    POSITIVE LOGITS
    _PLATFORM
    0.08
     slideshow
    0.08
    驾车
    0.07
    Recipe
    0.07
    :CGRect
    0.07
    盛宴
    0.06
    Have
    0.06
    -best
    0.06
     Press
    0.06
    宣传片
    0.06
    Activations Density 0.001%

    No Known Activations