© 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. 9976
    Prev
    Next
    INDEX
    Explanations

    abyss words, -st endings

    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
    ľ
    -0.06
    æĹłæīĢ
    -0.06
    ære
    -0.06
    EDI
    -0.05
    ÙİÙī
    -0.05
    upra
    -0.05
    chia
    -0.05
     (
    -0.05
    Ùī
    -0.05
    ä½ķä¸į
    -0.05
    POSITIVE LOGITS
    **–
    0.08
     Fucking
    0.08
    åŃ£åIJİ
    0.08
    añ
    0.08
    utnik
    0.08
    åIJĮæ¯Ķåĩıå°ij
    0.08
    ä¸Ģèµ·åģļ
    0.08
    ráf
    0.08
    KHTML
    0.08
    _NONNULL
    0.08
    Activations Density 1.493%

    No Known Activations