© 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. 22-TRANSCODER-HP
    7. 97843
    Prev
    Next
    INDEX
    Explanations

    Product recommendations/disclaimers; misc

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    E
    -0.28
    -so
    -0.27
     E
    -0.27
    大
    -0.26
    åIJĪæł¼
    -0.26
     bo
    -0.26
    大å±Ģ
    -0.25
     dr
    -0.25
     empty
    -0.25
     equally
    -0.24
    POSITIVE LOGITS
    okit
    0.33
    asive
    0.29
    stras
    0.27
     linea
    0.27
    ograph
    0.26
     liner
    0.26
     subtitle
    0.26
    odiac
    0.25
    lijke
    0.25
    ç»ıèIJ¥ç®¡çIJĨ
    0.24
    Activations Density 0.015%

    No Known Activations