© 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. 75523
    Prev
    Next
    INDEX
    Explanations

    articles

    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
    .coord
    -0.08
    Closing
    -0.07
    iosis
    -0.07
     Choice
    -0.07
     mourning
    -0.07
     casing
    -0.07
    loser
    -0.07
    nesia
    -0.06
    \Middleware
    -0.06
    ונה
    -0.06
    POSITIVE LOGITS
    植物
    0.08
     JM
    0.07
    _Q
    0.06
    崔
    0.06
    �
    0.06
     элект
    0.06
    GLenum
    0.06
     merchant
    0.06
     Duc
    0.06
    多万
    0.06
    Activations Density 0.017%

    No Known Activations