© 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. 142192
    Prev
    Next
    INDEX
    Explanations

    more

    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
    èĩªæĿ¥
    -0.27
    ede
    -0.25
    æĵļ
    -0.24
    åĬłå¿«å»ºè®¾
    -0.24
    西路
    -0.23
    etri
    -0.23
     marty
    -0.23
    è¯ħ
    -0.23
    opal
    -0.23
     Crimson
    -0.23
    POSITIVE LOGITS
     overload
    0.27
     orth
    0.27
    稳
    0.27
    åĨ²
    0.26
    ÎĶ
    0.26
    ä¸įå¿ĺ
    0.26
    imet
    0.26
    backs
    0.26
     ÎĶ
    0.25
    ortho
    0.25
    Activations Density 5.683%

    No Known Activations