© 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. 25-TRANSCODER-HP
    7. 109244
    Prev
    Next
    INDEX
    Explanations

    9 or 0

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     supplement
    -0.27
    è¿ĶåĽŀæIJľçĭIJ
    -0.25
    èįª
    -0.25
    åħ¬åı¸ç«łç¨ĭ
    -0.24
    iture
    -0.24
     miesz
    -0.24
     Politico
    -0.24
     Overrides
    -0.24
    iquement
    -0.24
    odiac
    -0.24
    POSITIVE LOGITS
    æĢªçī©
    0.34
    hrs
    0.27
    çļĦæīĭ
    0.26
    hma
    0.26
    åºĬä¸Ĭ
    0.25
    è¿Ļä¸Ģ
    0.25
    çķ¸å½¢
    0.25
    å¦ĸæĢª
    0.24
     gamm
    0.24
    çļĦ家åºŃ
    0.24
    Activations Density 0.905%

    No Known Activations