© 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. 29853
    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
    agger
    -0.29
     cash
    -0.26
    ↵↵
    -0.26
     delayed
    -0.25
     gar
    -0.25
    CACHE
    -0.25
    ä¸ĢåĪĨ
    -0.24
    hek
    -0.24
    agu
    -0.24
    _
    -0.24
    POSITIVE LOGITS
     Licence
    0.27
    注åħ¥
    0.27
     mould
    0.26
    èĤĵ
    0.26
    说ä»Ģä¹Ī
    0.26
    >;č↵
    0.25
    è¡ħ
    0.25
    PTY
    0.25
    åħ¥åºĵ
    0.25
    å¼ı
    0.25
    Activations Density 0.846%

    No Known Activations