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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 49910
    Prev
    Next
    INDEX
    Explanations

    Dramatic story excerpts

    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
     myfile
    -0.07
    fill
    -0.07
     underestimate
    -0.07
    海报
    -0.07
    .isNotBlank
    -0.07
    confirmed
    -0.06
    ࡑ
    -0.06
    .pe
    -0.06
    dbc
    -0.06
     routes
    -0.06
    POSITIVE LOGITS
     rout
    0.08
    KK
    0.08
     Guarantee
    0.07
    _brightness
    0.07
    FH
    0.07
    ,bool
    0.07
    birthday
    0.07
    gregar
    0.07
    itat
    0.07
    .Tick
    0.07
    Activations Density 0.016%

    No Known Activations