© 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. 107224
    Prev
    Next
    INDEX
    Explanations

    Punctuation and common words

    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
    为åħ¶
    -0.32
    黯
    -0.27
    å¤ĸåĽ´
    -0.27
    åIJİéĿ¢çļĦ
    -0.26
    èĵ¼
    -0.25
    @login
    -0.25
    requests
    -0.24
    _der
    -0.24
    为ä¹ĭ
    -0.24
    THIS
    -0.24
    POSITIVE LOGITS
    çĭ¬ç«ĭ
    0.31
    çį¨ç«ĭ
    0.30
     independents
    0.29
    aday
    0.27
    åĪ«
    0.26
    æħij
    0.25
    FetchRequest
    0.25
    urat
    0.25
    éķ¿çŁŃ
    0.25
     independence
    0.24
    Activations Density 76.400%

    No Known Activations