© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 89527
    Prev
    Next
    INDEX
    Explanations

    take

    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
    一定会
    -0.08
     adults
    -0.07
     difficulties
    -0.07
    ("(
    -0.07
     ui
    -0.07
    semester
    -0.07
    意见反馈
    -0.07
     effectiveness
    -0.07
     parenthesis
    -0.07
    (matches
    -0.07
    POSITIVE LOGITS
    螯
    0.08
     lẫn
    0.08
     предост
    0.08
    ืน
    0.07
    -other
    0.07
     ככל
    0.07
     @$_
    0.07
    _raw
    0.07
    بذ
    0.07
    現實
    0.06
    Activations Density 0.026%

    No Known Activations