© 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. 110934
    Prev
    Next
    INDEX
    Explanations

    News articles

    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
    ãģ¬
    -0.25
    å°ıå§IJ
    -0.25
    noxious
    -0.24
    PageIndex
    -0.24
    èį¤
    -0.24
    ç§ĺ书éķ¿
    -0.24
    atsby
    -0.24
    à¸IJ
    -0.24
    heels
    -0.24
    ewan
    -0.23
    POSITIVE LOGITS
    invert
    0.26
     hereby
    0.26
    票æį®
    0.25
    åĭ¾
    0.25
    ä¸ī级
    0.25
    å¾ħ
    0.25
    iter
    0.25
    dist
    0.24
    ä½ĵè´¨
    0.24
    夷
    0.24
    Activations Density 0.002%

    No Known Activations