© 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. 111084
    Prev
    Next
    INDEX
    Explanations

    clear

    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
    ettings
    -0.26
    olvable
    -0.24
     Sü
    -0.24
    ä½ķå¤Ħ
    -0.24
    descr
    -0.24
    CursorPosition
    -0.23
    prite
    -0.23
    ucker
    -0.23
    erial
    -0.23
     Horny
    -0.23
    POSITIVE LOGITS
    away
    0.30
     enough
    0.29
    cut
    0.28
    -cut
    0.28
    down
    0.28
    board
    0.28
    headed
    0.27
    -eyed
    0.27
     down
    0.26
    wis
    0.25
    Activations Density 0.319%

    No Known Activations