© 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. 107895
    Prev
    Next
    INDEX
    Explanations

    the

    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
    åİŁæĿ¥æĺ¯
    -0.28
    MethodInfo
    -0.26
    ë±ħ
    -0.26
    {{--
    -0.25
     yen
    -0.25
    è¿ĻéĩĮæľī
    -0.24
     `_
    -0.24
    rost
    -0.24
    [name
    -0.23
    à®ĥ
    -0.23
    POSITIVE LOGITS
    æĢ§å¼º
    0.28
     goose
    0.28
    æĤ´
    0.25
    UAL
    0.25
     guarantee
    0.25
    å·¥ä¸ļ
    0.24
     Eag
    0.24
     competed
    0.24
     RCMP
    0.24
    reuse
    0.24
    Activations Density 0.021%

    No Known Activations