© 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. 99038
    Prev
    Next
    INDEX
    Explanations

    1

    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
    ULATOR
    -0.26
    inke
    -0.25
    ieres
    -0.24
     Ãł
    -0.24
    尽头
    -0.24
    çĥŁçģ«
    -0.24
    ammen
    -0.24
     basics
    -0.24
     Bes
    -0.24
    ettes
    -0.24
    POSITIVE LOGITS
    _mut
    0.25
    æŃ£åľ¨è¿Ľè¡Į
    0.24
     fals
    0.24
    _panel
    0.23
    éĢļçŁ¥ä¹¦
    0.23
    æħ¶
    0.23
    缸äºĴ
    0.23
    æĺ¯åIJ¦æľī
    0.23
    hib
    0.22
     Honest
    0.22
    Activations Density 0.010%

    No Known Activations