© 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. 109685
    Prev
    Next
    INDEX
    Explanations

    Numbers

    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
     sore
    -0.07
    vel
    -0.07
    estation
    -0.07
    queueReusable
    -0.07
     ara
    -0.07
    ตาม
    -0.07
    روم
    -0.06
    等到
    -0.06
    жить
    -0.06
     asoci
    -0.06
    POSITIVE LOGITS
     reproduce
    0.07
     элемент
    0.07
    سبوع
    0.07
    停产
    0.07
    (edge
    0.06
    ﰙ
    0.06
    _stop
    0.06
    เกษ
    0.06
    幅度
    0.06
    (record
    0.06
    Activations Density 0.003%

    No Known Activations