Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 29908
    Prev
    Next
    INDEX
    Explanations

    bead

    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
     cmap
    -0.06
    诱人
    -0.06
    Face
    -0.06
    otor
    -0.06
    fee
    -0.06
    给予了
    -0.06
     suffered
    -0.06
    ᬕ
    -0.06
     Quar
    -0.06
    Ban
    -0.06
    POSITIVE LOGITS
     Complex
    0.08
    .HttpServlet
    0.07
    ても
    0.07
    ة
    0.07
    耑
    0.07
     profiler
    0.07
     drains
    0.07
    œ
    0.07
    @media
    0.07
     произ
    0.07
    Activations Density 0.002%

    No Known Activations