© 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. 9-TRANSCODER-HP
    7. 29904
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç¾²
    -0.27
    CONTEXT
    -0.25
     XO
    -0.25
    down
    -0.25
    å¸ĮæľĽ
    -0.25
    parse
    -0.24
     Sark
    -0.24
     future
    -0.24
     hope
    -0.24
    æľºéģĩ
    -0.24
    POSITIVE LOGITS
    otics
    0.32
     Talk
    0.27
    ammers
    0.25
     Inch
    0.25
     thuê
    0.24
     incremented
    0.24
    è¯Ń
    0.24
     compound
    0.24
    å®°
    0.24
    enance
    0.24
    Activations Density 3.028%

    No Known Activations