© 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. 109611
    Prev
    Next
    INDEX
    Explanations

    dose

    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
    wr
    -0.07
    (Tag
    -0.07
     Middleware
    -0.07
    (Photo
    -0.07
     nad
    -0.07
    ("@
    -0.07
     Bed
    -0.07
    姿势
    -0.06
    (l
    -0.06
     latch
    -0.06
    POSITIVE LOGITS
     السنوات
    0.08
    텼
    0.07
    ผลกระท
    0.07
     americ
    0.07
    ක
    0.06
     Cannes
    0.06
    榰
    0.06
    센
    0.06
    颁布
    0.06
     lumière
    0.06
    Activations Density 0.067%

    No Known Activations