© 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. 108715
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    第ä¸ĢæĿ¡
    -0.28
    çļĦä¸Ģ项
    -0.28
    æİIJ
    -0.27
    ä¸Ģ项
    -0.26
    pirit
    -0.26
    è¿ĺæľī
    -0.25
    ZN
    -0.25
    è¾ĭ
    -0.25
    对åºĶ
    -0.25
    izin
    -0.25
    POSITIVE LOGITS
    olie
    0.28
     minority
    0.27
     testify
    0.26
     witnessing
    0.25
    éĿ
    0.25
    ucose
    0.25
    ä¸Ģäºĭ
    0.25
    jing
    0.25
    elor
    0.25
     //=
    0.25
    Activations Density 0.173%

    No Known Activations

    This feature has no known activations.