© 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. 111196
    Prev
    Next
    INDEX
    Explanations

    Code, names, and titles

    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
    å·ŀå¸Ĥ
    -0.28
    ermo
    -0.25
    èĻij
    -0.25
    ATAR
    -0.25
     zij
    -0.24
    ille
    -0.24
    GBT
    -0.24
    Subject
    -0.24
    åĵī
    -0.24
    rama
    -0.23
    POSITIVE LOGITS
    çļĦå°±æĺ¯
    0.28
     obsc
    0.28
    lip
    0.27
    WithContext
    0.25
    |[
    0.25
    anga
    0.25
    nop
    0.25
    inté
    0.24
     vag
    0.23
    FINE
    0.23
    Activations Density 0.001%

    No Known Activations