© 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. 3338
    Prev
    Next
    INDEX
    Explanations

    following punctuation

    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
    ï¼Ī
    -0.09
    ãĢįï¼Ī
    -0.09
     ï¼Ī
    -0.08
     (
    -0.08
    is
    -0.08
    ãĢıï¼Ī
    -0.07
     (=
    -0.07
    ;(
    -0.07
    (This
    -0.07
    ãĢĤï¼Ī
    -0.06
    POSITIVE LOGITS
    ï¼Łï¼ī
    0.12
    âĢ¦).
    0.10
    ä¸ĭ称
    0.10
    âĢ¦),
    0.10
    ä¿Ĺ称
    0.09
    ?).
    0.09
     tức
    0.09
    åį³
    0.09
    åį³ä»¥
    0.09
    åį³åĪ°
    0.09
    Activations Density 0.629%

    No Known Activations