© 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. 98920
    Prev
    Next
    INDEX
    Explanations

    the

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸Ģ份
    -0.27
    äºĨä¸Ģ份
    -0.26
    af
    -0.26
    ç»ĻäºĨæĪij
    -0.25
    (Func
    -0.25
    éĥ¨åĪĨ
    -0.24
    ç¾¹
    -0.24
    Ħ件
    -0.24
    (lib
    -0.24
    åħ¨æĹ¥
    -0.24
    POSITIVE LOGITS
    cou
    0.29
    slide
    0.29
    uate
    0.27
    åĨĽ
    0.27
     Ea
    0.26
    çĸı导
    0.25
     Ak
    0.25
    çŃ¹
    0.25
     propag
    0.24
    æĺ¼
    0.24
    Activations Density 0.001%

    No Known Activations