© 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. 63768
    Prev
    Next
    INDEX
    Explanations

    code or programming

    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
     perfectly
    -0.38
     perfect
    -0.37
     flawless
    -0.36
    Perfect
    -0.34
    perfect
    -0.34
    å®Įç¾İ
    -0.34
     Perfect
    -0.33
     perfection
    -0.33
    å®Įç¾İçļĦ
    -0.33
    çĻ¾åĪĨçĻ¾
    -0.31
    POSITIVE LOGITS
     unknown
    0.30
    s
    0.30
    0.29
    ä¸įéĢĤåIJĪ
    0.28
    Unknown
    0.28
    ä¸įçŁ¥
    0.28
    ä¸įåħ·å¤ĩ
    0.28
     cur
    0.27
    åŁĭ
    0.27
     bar
    0.27
    Activations Density 74.604%

    No Known Activations