© 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. 86831
    Prev
    Next
    INDEX
    Explanations

    final, last

    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
    åĿļåĽº
    -0.27
    缸åħ³åĨħ容
    -0.26
    ichel
    -0.23
    ovsky
    -0.23
    深交
    -0.23
    åıªæĺ¯ä¸ºäºĨ
    -0.23
    ç¨³åĽº
    -0.23
     Rogue
    -0.23
     separate
    -0.23
    :none
    -0.23
    POSITIVE LOGITS
    ipeg
    0.31
    é¾Ħ
    0.28
    REAK
    0.28
     omn
    0.25
     yyn
    0.24
    ĺìĿ´
    0.23
    cant
    0.23
     searchable
    0.23
    awy
    0.23
    æīŃ转
    0.23
    Activations Density 0.013%

    No Known Activations