© 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. 48497
    Prev
    Next
    INDEX
    Explanations

    lit

    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
     thanking
    -0.07
    אושר
    -0.07
    陉
    -0.07
     uncomfort
    -0.07
    不慎
    -0.07
    xious
    -0.07
    Claims
    -0.06
    overs
    -0.06
    隶属于
    -0.06
    ramid
    -0.06
    POSITIVE LOGITS
    _pag
    0.07
    录音
    0.07
    耶
    0.07
    录像
    0.07
     neb
    0.06
     Lucas
    0.06
     broadcasts
    0.06
    _gp
    0.06
    .lb
    0.06
    买
    0.06
    Activations Density 0.000%

    No Known Activations