© 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. 88658
    Prev
    Next
    INDEX
    Explanations

    digest

    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
    turned
    -0.28
    姿åĬ¿
    -0.24
    enton
    -0.24
    룴
    -0.23
    èĤĮèĤī
    -0.23
    deen
    -0.23
    é¦ģ
    -0.22
     Basics
    -0.22
     requestBody
    -0.22
    assage
    -0.22
    POSITIVE LOGITS
    ive
    0.34
    s
    0.33
     foam
    0.25
    iveness
    0.25
    uali
    0.25
    ination
    0.25
    y
    0.24
    á»į
    0.24
    schools
    0.23
    ful
    0.23
    Activations Density 0.088%

    No Known Activations