© 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. 97227
    Prev
    Next
    INDEX
    Explanations

    turbine

    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
     Monsters
    -0.27
    ä¸Ĭåīį
    -0.26
    äºĪ
    -0.26
    иÑĤеÑģÑĮ
    -0.25
    æļ´
    -0.25
    da
    -0.25
    dio
    -0.24
    propri
    -0.24
    enting
    -0.24
    ä»·
    -0.24
    POSITIVE LOGITS
    /action
    0.25
     crunch
    0.25
     flesh
    0.25
    æĸĩåĮĸ产ä¸ļ
    0.25
     collapsing
    0.24
     tact
    0.24
    bine
    0.23
    RuleContext
    0.23
     hurl
    0.23
    RequestMapping
    0.23
    Activations Density 0.178%

    No Known Activations