© 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. 86751
    Prev
    Next
    INDEX
    Explanations

    questions and answers

    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
    nty
    -0.28
    å¼Ģ
    -0.27
    æĬ¬
    -0.25
     ici
    -0.25
    ูà¸ģ
    -0.24
     cites
    -0.24
    ahoo
    -0.24
    驾
    -0.24
    é¦Ļ
    -0.24
     maturity
    -0.23
    POSITIVE LOGITS
    å°ıæŶåīį
    0.29
    ({_
    0.26
    äm
    0.26
    brig
    0.26
    (_)
    0.25
     mig
    0.25
    âĢ¦)↵↵
    0.25
    åīįæıIJæĺ¯
    0.25
    åĩłä¸ªäºº
    0.24
    è¿ĩç¨ĭå½ĵä¸Ń
    0.24
    Activations Density 0.239%

    No Known Activations