© 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. 23-TRANSCODER-HP
    7. 25376
    Prev
    Next
    INDEX
    Explanations

    til

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    大æ´ĭ
    -0.28
    stras
    -0.27
    ä¹ŁåºĶ该
    -0.27
     comm
    -0.26
    ought
    -0.26
    ä¹Łæľīä¸ĢäºĽ
    -0.25
     deep
    -0.25
     sheets
    -0.25
     sand
    -0.25
     post
    -0.25
    POSITIVE LOGITS
    æłij
    0.27
     -$
    0.26
    aurus
    0.26
    èµIJ
    0.26
    åIJĿ
    0.25
     Toolbox
    0.25
    æĥ«
    0.25
    .getServer
    0.25
     Spr
    0.24
     Conflict
    0.24
    Activations Density 0.047%

    No Known Activations