© 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. 108512
    Prev
    Next
    INDEX
    Explanations

    data streams and processing

    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
     inertia
    -0.30
     Camel
    -0.28
    ÂŃing
    -0.28
    ableObject
    -0.27
    åĸĦ
    -0.26
    atile
    -0.26
    uron
    -0.24
    大家åı¯ä»¥
    -0.24
    é©·
    -0.24
     UNIVERS
    -0.23
    POSITIVE LOGITS
    ity
    0.28
    ãģĵãģ¨
    0.27
    è¿·æĥij
    0.24
    quin
    0.23
     escrit
    0.23
    èĤ¡ä¸ľå¤§ä¼ļ
    0.23
    cord
    0.23
     decor
    0.23
    ä¼ĺåĬ¿
    0.23
    æĿĨèıĮ
    0.23
    Activations Density 0.943%

    No Known Activations