© 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. 108353
    Prev
    Next
    INDEX
    Explanations

    Descriptive text

    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
    _VO
    -0.27
    åĨľå®¶
    -0.26
    onest
    -0.25
    ogl
    -0.25
    ç¡®å®ŀ
    -0.24
    æĺ¾çĦ¶
    -0.24
    å±ŀå®ŀ
    -0.23
    onces
    -0.23
    YO
    -0.23
    ç½®ãģĦãģ¦
    -0.23
    POSITIVE LOGITS
    âĢķâĢķ
    0.35
    åį³
    0.31
    ——
    0.31
    ä¹Łå°±æĺ¯
    0.31
     namely
    0.27
    代表
    0.26
    ield
    0.26
    .GetChild
    0.26
    |--
    0.25
    —in
    0.24
    Activations Density 32.848%

    No Known Activations