© 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. 42094
    Prev
    Next
    INDEX
    Explanations

    4

    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
    æı¡
    -0.31
     play
    -0.28
    æĬ½æŁ¥
    -0.26
    play
    -0.26
    ä¿®çIJĨ
    -0.26
    morph
    -0.26
    	play
    -0.24
    å·¥
    -0.24
    MASK
    -0.24
    è¿Ľåº¦
    -0.24
    POSITIVE LOGITS
    _passed
    0.28
    å¾®å¦Ļ
    0.28
    微微
    0.27
     Nh
    0.27
    NR
    0.26
    åı¯æĮģç»Ń
    0.26
    廳
    0.25
    лон
    0.25
    aud
    0.24
     passing
    0.24
    Activations Density 0.001%

    No Known Activations