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. 19-RESID-POST-AA
    6. 59858
    Prev
    Next
    INDEX
    Explanations

    -get

    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
     appreciation
    -0.07
    ecute
    -0.07
    区别
    -0.07
    _VAL
    -0.07
    わけ
    -0.07
     propulsion
    -0.07
    _VALUES
    -0.06
    照料
    -0.06
    ayer
    -0.06
    入睡
    -0.06
    POSITIVE LOGITS
    PP
    0.06
    蚂
    0.06
     kcal
    0.06
    ✏
    0.06
    榔
    0.06
     노
    0.06
     GG
    0.06
    .rabbit
    0.06
    嵋
    0.06
     метро
    0.06
    Activations Density 0.004%

    No Known Activations