© 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. 108213
    Prev
    Next
    INDEX
    Explanations

    source code

    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
    æĽ¿ä»£
    -0.45
     replacing
    -0.40
     occupy
    -0.39
    æĭħä»»
    -0.39
     replace
    -0.39
     assigned
    -0.36
     replaces
    -0.36
    replace
    -0.36
    åįłæį®
    -0.36
     occupying
    -0.36
    POSITIVE LOGITS
     bureauc
    0.29
     autob
    0.29
    ä¸ŃåĽ½äºº
    0.28
    æµģæĺŁ
    0.28
    iens
    0.25
     Ney
    0.25
    ,eg
    0.25
    dad
    0.25
    YSIS
    0.25
    ве
    0.25
    Activations Density 1.064%

    No Known Activations