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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 109076
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     locations
    -0.28
    (Tag
    -0.27
    gmail
    -0.25
    ение
    -0.25
    noinspection
    -0.25
    çľ¼
    -0.25
    ä¸įä½ı
    -0.25
    getLocation
    -0.25
     identification
    -0.25
    ë°
    -0.24
    POSITIVE LOGITS
    秣
    0.29
    -nil
    0.26
    uset
    0.26
    '}}↵
    0.26
    ä¸ĭ游
    0.25
    ạng
    0.25
    çľĭä¸Ģçľĭ
    0.25
    襦
    0.25
    ä¸Ĭ游
    0.25
     Metropolitan
    0.25
    Activations Density 1.121%

    No Known Activations