© 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. 14-TRANSCODER-HP
    7. 41479
    Prev
    Next
    INDEX
    Explanations

    composition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ardy
    -0.32
     sut
    -0.28
    æīĭåĬ¨
    -0.26
     ro
    -0.25
     beg
    -0.24
     shed
    -0.24
    rio
    -0.24
    ark
    -0.23
    åī¥
    -0.23
    )-(
    -0.23
    POSITIVE LOGITS
    ä¸įèĪĴæľį
    0.30
    cop
    0.29
    {{$
    0.26
    datum
    0.26
    æ²»å®ī
    0.25
    WithDuration
    0.25
    COVER
    0.25
    [element
    0.24
    >NN
    0.24
    æģ¯
    0.24
    Activations Density 2.717%

    No Known Activations