© 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. 109177
    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
    mund
    -0.30
    ä¸ĵä¸ļçļĦ
    -0.27
     oppon
    -0.27
    积累äºĨ
    -0.26
    ä¾ĽéľĢ
    -0.26
     pinch
    -0.26
    umd
    -0.26
    çŁŃæľŁ
    -0.25
    bjerg
    -0.25
    çŁŃ缺
    -0.25
    POSITIVE LOGITS
    T
    0.28
     Clo
    0.28
     Del
    0.28
    à¹Ģลย
    0.27
     forever
    0.26
     points
    0.26
    TURE
    0.25
     trụ
    0.25
     CC
    0.25
     T
    0.24
    Activations Density 3.002%

    No Known Activations

    This feature has no known activations.