© 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. 99177
    Prev
    Next
    INDEX
    Explanations

    central

    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
    phere
    -0.23
     quo
    -0.23
    ï¬ĥ
    -0.23
    syn
    -0.23
    棱
    -0.23
    edges
    -0.23
    etting
    -0.23
    ç»Ī端
    -0.23
    cts
    -0.23
    éĻIJãĤĬ
    -0.23
    POSITIVE LOGITS
    izados
    0.31
    izado
    0.30
    家ä¼Ļ
    0.28
    itate
    0.27
    æıIJä¾ĽçļĦ
    0.27
    mente
    0.26
    ifix
    0.25
    ities
    0.25
    isé
    0.25
    izada
    0.24
    Activations Density 0.206%

    No Known Activations