© 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. 130426
    Prev
    Next
    INDEX
    Explanations

    These

    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
    ä»ĸèĩªå·±
    -0.28
    åįıè°ĥ
    -0.27
    aning
    -0.26
    vin
    -0.26
     fet
    -0.25
    ç«¿
    -0.25
    ania
    -0.24
    åŁİå¸Ĥ建设
    -0.24
    åıĪ
    -0.24
    än
    -0.24
    POSITIVE LOGITS
    ephy
    0.25
    blink
    0.24
     Sikh
    0.23
    è¿Ļæĺ¯æĪij
    0.23
    hdl
    0.22
     Taste
    0.22
    <Class
    0.22
    è¯İ
    0.22
    PACE
    0.22
    ptime
    0.22
    Activations Density 0.006%

    No Known Activations