© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6637
    Prev
    Next
    INDEX
    Explanations

    Church

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Known
    -0.24
     GridView
    -0.24
     Logged
    -0.24
     ConfigureServices
    -0.24
    ccount
    -0.24
     ``(
    -0.23
     Albums
    -0.23
    è¹ī
    -0.23
    滹
    -0.23
    _whitespace
    -0.23
    POSITIVE LOGITS
    less
    0.33
    è¡Ļ
    0.31
    yas
    0.28
    ç»ĵæŀĦ
    0.27
    yard
    0.26
    éĿĴ
    0.25
     hall
    0.25
    社
    0.25
    ç¥ŀ
    0.25
    nas
    0.25
    Activations Density 2.065%

    No Known Activations