© 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. 130929
    Prev
    Next
    INDEX
    Explanations

    Legal/official responses

    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
    Not in Any Lists

    No Comments

    Negative Logits
     ko
    -0.26
    åijĭ
    -0.26
     aff
    -0.24
     Spicer
    -0.24
    offee
    -0.24
    æĹĥ
    -0.24
     hammer
    -0.24
    ç¿°
    -0.23
     storm
    -0.23
    Tonight
    -0.23
    POSITIVE LOGITS
    trap
    0.33
    çļĦè¦ģæ±Ĥ
    0.31
    çŃĶåºĶ
    0.28
     requests
    0.28
    .jd
    0.28
    TRA
    0.28
    arel
    0.27
    ino
    0.27
    建议
    0.27
    requests
    0.26
    Activations Density 0.038%

    No Known Activations