© 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. 113177
    Prev
    Next
    INDEX
    Explanations

    Approximation and comparison words

    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
    Ãłng
    -0.28
     faithful
    -0.27
    alon
    -0.27
    PFN
    -0.27
    gnore
    -0.24
    è°Ľ
    -0.24
    ocket
    -0.24
    ç»ıèIJ¥ç®¡çIJĨ
    -0.23
    åīį身
    -0.23
     materially
    -0.23
    POSITIVE LOGITS
    vero
    0.28
    sse
    0.26
     ticking
    0.25
     dun
    0.24
     Schedule
    0.24
    diff
    0.24
    nton
    0.24
    bulan
    0.24
    ubic
    0.24
    ich
    0.24
    Activations Density 0.007%

    No Known Activations