© 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. 15-RESID-POST-AA
    6. 40108
    Prev
    Next
    INDEX
    Explanations

    Length measurements

    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
    ться
    -0.07
    errated
    -0.07
     suck
    -0.06
    (mu
    -0.06
    욯
    -0.06
    ያ
    -0.06
    ikit
    -0.06
    .lists
    -0.06
    国度
    -0.06
    앚
    -0.06
    POSITIVE LOGITS
    (Session
    0.07
    蝙
    0.07
    ホテ
    0.07
     THE
    0.07
    carbon
    0.07
    工商联
    0.07
     rapport
    0.07
     quil
    0.07
    DAY
    0.07
     drama
    0.06
    Activations Density 0.005%

    No Known Activations