© 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. 20-TRANSCODER-HP
    7. 64256
    Prev
    Next
    INDEX
    Explanations

    recommendations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Link
    -0.27
    amu
    -0.27
     <=>
    -0.25
    ATIC
    -0.25
    chio
    -0.25
    ETS
    -0.25
    chia
    -0.25
     Ksi
    -0.24
     sẵn
    -0.24
    æ³Ħ
    -0.24
    POSITIVE LOGITS
    ä¸įåħĭ
    0.27
    iali
    0.26
    åįĥåħĥ
    0.25
     nett
    0.25
    å¤ĸåĽ´
    0.24
    çķª
    0.24
    ston
    0.24
    æĶ¶
    0.24
     silent
    0.24
    çļĦåľ°ä½į
    0.24
    Activations Density 13.665%

    No Known Activations