© 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. 107618
    Prev
    Next
    INDEX
    Explanations

    technology

    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
     nowhere
    -0.34
    LLU
    -0.31
    ä¸įç®Ĺ
    -0.29
     Nope
    -0.28
    å°ijè§ģ
    -0.28
    æĺ¯ä¸įåı¯èĥ½
    -0.27
    并ä¸įä¼ļ
    -0.27
     ìĹĨìĬµëĭĪëĭ¤
    -0.26
    .none
    -0.26
     moot
    -0.26
    POSITIVE LOGITS
    unal
    0.28
     lun
    0.27
     cub
    0.27
    achten
    0.26
    好å¤ļ
    0.25
    out
    0.25
    禮
    0.24
    对å¾ħ
    0.24
    ffective
    0.24
    ØŃÙĨ
    0.24
    Activations Density 36.432%

    No Known Activations