© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 7662
    Prev
    Next
    INDEX
    Explanations

    research

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    è¾ĵåĩº
    -0.28
    emo
    -0.28
    æ·±åĪ»çļĦ
    -0.26
    æ°¸è¿ľ
    -0.26
    裸
    -0.26
    ä¸ĭåįĬ
    -0.26
    éģĵå¾·
    -0.25
    åħ¸åŀĭçļĦ
    -0.25
    èĶº
    -0.25
    exe
    -0.25
    POSITIVE LOGITS
     beneficial
    0.31
     research
    0.29
     researched
    0.29
     benefits
    0.28
     claims
    0.28
     wiki
    0.27
     anecd
    0.27
    èĩªä¸»åĪĽæĸ°
    0.26
     researching
    0.26
     rejuven
    0.26
    Activations Density 0.002%

    No Known Activations