© 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. 7832
    Prev
    Next
    INDEX
    Explanations

    collections, repertories

    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
    临
    -0.35
    款
    -0.31
    课åłĤ
    -0.29
    æķĻä¼ļ
    -0.27
    è´¹
    -0.26
    ajo
    -0.24
     gra
    -0.24
    adio
    -0.24
    çļĦäºĭ
    -0.24
    éĢŁåº¦
    -0.23
    POSITIVE LOGITS
    egot
    0.30
    ç³Ĺ
    0.27
    èĥľä»»
    0.25
    frog
    0.24
     riv
    0.24
     ÑģобÑĢан
    0.24
    éĸ£
    0.23
    _written
    0.23
    ä¼°åĢ¼
    0.23
     Riv
    0.23
    Activations Density 0.033%

    No Known Activations