© 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. 89472
    Prev
    Next
    INDEX
    Explanations

    choosing from a list

    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
    bbie
    -0.08
     تريد
    -0.07
    หร
    -0.07
     Stamford
    -0.07
     tiene
    -0.07
     fulfillment
    -0.07
    междуна
    -0.07
    mutable
    -0.07
    答え
    -0.07
    營
    -0.07
    POSITIVE LOGITS
    SetTitle
    0.07
    혭
    0.07
     disappointed
    0.06
     embraced
    0.06
    ench
    0.06
    招呼
    0.06
    ItemCount
    0.06
     الجو
    0.06
    )])↵
    0.06
    Social
    0.06
    Activations Density 0.067%

    No Known Activations