© 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. 112829
    Prev
    Next
    INDEX
    Explanations

    Website addresses

    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
     Official
    -0.32
     https
    -0.30
    绸
    -0.29
    å®ĺæĸ¹
    -0.29
    Official
    -0.27
    ç§ijåѦ
    -0.26
    orsche
    -0.26
    ord
    -0.26
    https
    -0.26
     official
    -0.26
    POSITIVE LOGITS
     refs
    0.27
    .Tags
    0.25
    ariate
    0.25
    branches
    0.25
     recurs
    0.25
    -tags
    0.24
    åĽ¢éķ¿
    0.24
     bookmarks
    0.24
    ç¿»
    0.24
     pleasantly
    0.24
    Activations Density 0.010%

    No Known Activations