© 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. 32-TRANSCODER-HP
    7. 42857
    Prev
    Next
    INDEX
    Explanations

    Punctuation and text matching

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asu
    -0.29
    URY
    -0.27
    èģĶ缣
    -0.26
    oor
    -0.26
     raining
    -0.26
    .setLayout
    -0.25
    -ln
    -0.25
    ç«łç¨ĭ
    -0.25
    zte
    -0.24
    èĨ³
    -0.24
    POSITIVE LOGITS
     match
    0.31
    -period
    0.30
    period
    0.28
    管çIJĨ模å¼ı
    0.28
     smooth
    0.28
     period
    0.27
     Match
    0.27
     Period
    0.27
    Period
    0.27
    match
    0.27
    Activations Density 0.001%

    No Known Activations