© 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. 107442
    Prev
    Next
    INDEX
    Explanations

    English

    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
    ahead
    -0.28
    nal
    -0.26
    omon
    -0.25
    \Common
    -0.25
    åľºä¸Ĭ
    -0.24
    sexual
    -0.24
    足
    -0.24
    ä¸Ń级
    -0.24
    EXTERNAL
    -0.24
    PLAN
    -0.23
    POSITIVE LOGITS
    fcc
    0.25
    æĬ¬å¤´
    0.23
    罩
    0.23
    èĽĢ
    0.23
    ments
    0.23
     اÙĦÙĤÙĪÙħÙĬ
    0.23
    åįİåįĹ
    0.23
    ãĤ§
    0.23
    aic
    0.23
     @_
    0.23
    Activations Density 11.071%

    No Known Activations