© 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. 113004
    Prev
    Next
    INDEX
    Explanations

    Helping verbs

    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
    .IsSuccess
    -0.28
    ridged
    -0.28
    æĴŃæĬ¥
    -0.25
     nas
    -0.25
    omens
    -0.25
    eo
    -0.24
    å±Ģéķ¿
    -0.24
    建åįİ
    -0.23
    (red
    -0.23
    (""
    -0.23
    POSITIVE LOGITS
    è¡¡
    0.30
    st
    0.27
    Fi
    0.27
     Fi
    0.27
    æIJŀ
    0.27
     impl
    0.25
    dest
    0.25
    OF
    0.25
    注
    0.25
    sti
    0.24
    Activations Density 0.042%

    No Known Activations