© 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. 141369
    Prev
    Next
    INDEX
    Explanations

    Names and article introductions

    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
     bothered
    -0.27
    æ´Ļ
    -0.27
    ä¸įèĥ½åĨį
    -0.27
    æĪIJ为ä¸Ģ个
    -0.26
    éļĪ
    -0.26
    鲫
    -0.26
    份
    -0.25
    ä¸Ģçľ¼
    -0.25
    çIJĽ
    -0.25
    çĻ½çĻ½
    -0.24
    POSITIVE LOGITS
    ugen
    0.31
    mit
    0.28
    à¤ł
    0.27
    ä»įæĺ¯
    0.27
    ìĤ¬
    0.26
    bau
    0.26
    rcode
    0.26
    æŃĮ
    0.26
     still
    0.25
     ofType
    0.25
    Activations Density 3.233%

    No Known Activations