© 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. 22-TRANSCODER-HP
    7. 99051
    Prev
    Next
    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æľ¬æ¬¡
    -0.28
    åħľ
    -0.26
    _posts
    -0.26
    æľ¬æĽ¸
    -0.26
    æľ¬ä¹¦
    -0.25
    ä»ĬåĽŀãģ®
    -0.25
    å¶Ĥ
    -0.25
    æľ¬æ¡Ī
    -0.25
     perce
    -0.24
    rror
    -0.24
    POSITIVE LOGITS
    è£Ĥ
    0.28
    æı´
    0.27
    Fetcher
    0.25
    codile
    0.25
    abr
    0.25
    acher
    0.25
     talking
    0.24
    ä¸įå®ļ
    0.24
    ascar
    0.24
    å®īç½®
    0.24
    Activations Density 0.013%

    No Known Activations