© 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. 30-TRANSCODER-HP
    7. 96272
    Prev
    Next
    INDEX
    Explanations

    code punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     factor
    -0.28
    atorio
    -0.28
     approximation
    -0.27
     net
    -0.26
     {}.
    -0.26
    åŁ
    -0.26
    wró
    -0.25
     PT
    -0.25
     vene
    -0.25
    ↵                        ↵
    -0.25
    POSITIVE LOGITS
    0.38
    壮
    0.32
    0.31
    okies
    0.29
     agre
    0.29
    份
    0.28
    åı¥
    0.28
    ³³³
    0.27
    æľīéĻIJ
    0.26
    åģľçķĻ
    0.26
    Activations Density 0.416%

    No Known Activations