© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9090
    Prev
    Next
    INDEX
    Explanations

    get

    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
     выз
    -0.08
    ก
    -0.07
     circa
    -0.07
     эксп
    -0.07
    _access
    -0.07
     endorsing
    -0.07
    盼
    -0.07
     Hart
    -0.07
     الس
    -0.07
    识
    -0.07
    POSITIVE LOGITS
    טכנולוגיה
    0.07
     getEmail
    0.07
    ourses
    0.07
    leştirme
    0.07
    Coupon
    0.07
    락
    0.06
    tığımız
    0.06
    摔倒
    0.06
    _EOL
    0.06
     Route
    0.06
    Activations Density 0.023%

    No Known Activations