© 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. 30-TRANSCODER-HP
    7. 97120
    Prev
    Next
    INDEX
    Explanations

    biological structures

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æŀķ
    -0.29
    å¯Ĥå¯ŀ
    -0.28
     civilized
    -0.28
    æŀķ头
    -0.28
    alon
    -0.27
     news
    -0.27
    mate
    -0.27
     polite
    -0.26
    ream
    -0.25
    åĵij
    -0.24
    POSITIVE LOGITS
    åĩĢåĢ¼
    0.31
    å¿ĥè¡Ģ
    0.29
    ensed
    0.28
    isable
    0.27
    åĻ¨
    0.26
    å¿ĥ
    0.26
    serialization
    0.25
    earn
    0.25
    éļĻ
    0.25
    earned
    0.25
    Activations Density 0.112%

    No Known Activations