© 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. 97187
    Prev
    Next
    INDEX
    Explanations

    computer-related 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
    elib
    -0.29
    inqu
    -0.28
     crossed
    -0.28
    anne
    -0.24
     Hend
    -0.24
    stood
    -0.24
    mk
    -0.24
    _depend
    -0.24
    deen
    -0.24
    æķ£
    -0.24
    POSITIVE LOGITS
    ei
    0.27
    aden
    0.25
    ç¹ĩ
    0.25
    æ²Ļé¾Ļ
    0.25
    /banner
    0.25
     Gallup
    0.24
    aker
    0.24
    ffffff
    0.24
    eryl
    0.23
    缦
    0.23
    Activations Density 0.007%

    No Known Activations