© 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. 63267
    Prev
    Next
    INDEX
    Explanations

    Technical/Scientific writing

    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
     they
    -0.29
    жен
    -0.27
     fil
    -0.26
    unct
    -0.26
     StringField
    -0.26
    ä»ĸ们
    -0.26
     They
    -0.25
     am
    -0.25
    ×£
    -0.25
    \x
    -0.25
    POSITIVE LOGITS
    ervoir
    0.27
    åħ¥åºĵ
    0.26
    herits
    0.25
     Cush
    0.25
    æĺ¯ä»ĸ
    0.25
     MODE
    0.25
    maal
    0.24
    åħ±åIJĮåıijå±ķ
    0.24
     unre
    0.24
    为æĬĵ
    0.24
    Activations Density 6.860%

    No Known Activations