© 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. 108003
    Prev
    Next
    INDEX
    Explanations

    conut

    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
    ment
    -0.28
    mente
    -0.27
    -priced
    -0.27
    ments
    -0.27
    ixo
    -0.26
    MENTS
    -0.25
    su
    -0.24
     ment
    -0.24
    emente
    -0.24
    æ¸ļ
    -0.24
    POSITIVE LOGITS
    ãĢĤãĢĮ
    0.26
    é¦Ļèķī
    0.25
    çĩ¥
    0.24
    èĬ¯
    0.24
     dra
    0.24
     unus
    0.24
     sack
    0.23
    Mixed
    0.23
    lius
    0.23
    ograph
    0.23
    Activations Density 3.497%

    No Known Activations