© 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. 141106
    Prev
    Next
    INDEX
    Explanations

    code, tech snippets

    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
    -ring
    -0.27
    /************************
    -0.27
    _$_
    -0.26
     rings
    -0.25
    ç«£
    -0.25
    vier
    -0.24
     wipe
    -0.24
    =''
    -0.24
     louis
    -0.23
    irie
    -0.23
    POSITIVE LOGITS
    ennessee
    0.28
    çľĭä¸įè§ģ
    0.26
     Gos
    0.24
    æĬ¬å¤´
    0.24
    åıĹéĻIJ
    0.24
    CUS
    0.24
    æ¦Ĥ念
    0.23
     меÑĤалл
    0.23
    æĿ¥æºIJ
    0.23
    ç»ĨèĬĤ
    0.23
    Activations Density 14.342%

    No Known Activations