© 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. 97050
    Prev
    Next
    INDEX
    Explanations

    Roman

    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
    ground
    -0.29
    ward
    -0.28
    foot
    -0.28
    one
    -0.28
    forms
    -0.27
    /in
    -0.26
    rat
    -0.26
    æ®ĸ
    -0.25
    MS
    -0.25
    found
    -0.25
    POSITIVE LOGITS
    etty
    0.26
    romatic
    0.25
     Spo
    0.25
    笥
    0.24
     BSD
    0.24
     lick
    0.24
    éĵµ
    0.23
    aysia
    0.23
     Tale
    0.23
    romo
    0.23
    Activations Density 0.020%

    No Known Activations