© 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. 23-TRANSCODER-HP
    7. 23812
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ewire
    -0.28
    ģ
    -0.28
    çļĦæķ°éĩı
    -0.28
    å½ĵæŶçļĦ
    -0.28
    é¢ĦæľŁ
    -0.27
    éĽĨåĽ¢
    -0.26
    éĽĨåľĺ
    -0.26
    duct
    -0.26
     collaborations
    -0.26
     partnership
    -0.26
    POSITIVE LOGITS
    hang
    0.29
     hang
    0.26
    说起
    0.26
     départ
    0.25
    hua
    0.25
    ä¸įèī¯ä¿¡æģ¯
    0.25
     mog
    0.24
    å±ķ
    0.24
    Stars
    0.23
    ç¼ĺ
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.