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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 42605
    Prev
    Next
    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    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
    孤儿
    -0.07
     elf
    -0.07
    禊
    -0.07
     flavored
    -0.07
    ewolf
    -0.07
    *T
    -0.07
     Fool
    -0.07
    迎合
    -0.07
    cycl
    -0.07
     other
    -0.06
    POSITIVE LOGITS
    .tab
    0.07
     →↵↵
    0.07
    smooth
    0.07
    🌥
    0.06
    "/>.↵
    0.06
    ENCIL
    0.06
    :$
    0.06
     bathrooms
    0.06
    forward
    0.06
     signalling
    0.06
    Activations Density 0.031%

    No Known Activations