© 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. 86848
    Prev
    Next
    INDEX
    Explanations

    sut

    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
     MyApp
    -0.31
    ivering
    -0.27
    LocalizedString
    -0.25
    FRING
    -0.24
    ByText
    -0.24
    æ¬Ĭ
    -0.24
    bing
    -0.23
     univers
    -0.23
    afia
    -0.23
    \brief
    -0.23
    POSITIVE LOGITS
    没æĶ¶
    0.28
    åĽºçĦ¶
    0.26
    Ho
    0.26
    æµĩ
    0.25
    æĮģãģ¡
    0.25
     substitution
    0.25
    æĢ»ä½ĵ
    0.24
    éĺį
    0.24
     Charg
    0.24
     runner
    0.24
    Activations Density 0.003%

    No Known Activations