© 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. 141996
    Prev
    Next
    INDEX
    Explanations

    of and all

    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
     flips
    -0.26
    建设工ç¨ĭ
    -0.26
     Throne
    -0.25
    unde
    -0.24
     flip
    -0.24
     pedestal
    -0.24
    xDE
    -0.24
    ä¸į满
    -0.24
    lename
    -0.23
    æ±īè¯Ń
    -0.23
    POSITIVE LOGITS
    網
    0.27
    bes
    0.27
    æ®ĥ
    0.27
     taraf
    0.27
    çķĻ
    0.26
    illion
    0.25
    éħįåIJĪ
    0.24
    [U
    0.23
    çļĦåľ°æŃ¥
    0.23
    Saint
    0.23
    Activations Density 11.631%

    No Known Activations