© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 27300
    Prev
    Next
    INDEX
    Explanations

    $0$-fold composition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bruck
    -0.09
    irsch
    -0.09
    باش
    -0.08
    ersch
    -0.08
    åłĢ
    -0.07
    溪éķĩ
    -0.07
    ANGAN
    -0.07
    群ä¼Ĺåıįæĺł
    -0.07
    aseline
    -0.07
    _cast
    -0.07
    POSITIVE LOGITS
    空
    0.07
    空èĻļ
    0.07
     undefined
    0.07
    å±ħçĦ¶
    0.07
     empty
    0.07
    è¾ij
    0.07
    空çļĦ
    0.07
    空空
    0.07
    empty
    0.07
     mathematical
    0.06
    Activations Density 0.006%

    No Known Activations