© 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. 27-TRANSCODER-HP
    7. 9711
    Prev
    Next
    INDEX
    Explanations

    conceptual models

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    èªĵ
    -0.25
    lung
    -0.25
    IJèĹı
    -0.24
    fil
    -0.24
    åĩłå®¶
    -0.24
    åĪ«çļĦ
    -0.24
    fall
    -0.24
    åıªæĥ³
    -0.24
    erring
    -0.23
     otherwise
    -0.23
    POSITIVE LOGITS
    é«ĺåľ°
    0.29
    åĴĮæľįåĬ¡
    0.27
    .Listener
    0.26
    ứt
    0.25
    bers
    0.25
    æĪijè¿ĺ
    0.25
    izedName
    0.25
    sheets
    0.25
    Ä°Z
    0.25
    ize
    0.25
    Activations Density 0.791%

    No Known Activations