© 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. 24965
    Prev
    Next
    INDEX
    Explanations

    or followed by common 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
    esser
    -0.07
    APA
    -0.07
    erate
    -0.07
    ENDO
    -0.07
    ersh
    -0.07
    Lite
    -0.06
    åı¯å¾ª
    -0.06
    /../
    -0.06
    Å¡nj
    -0.06
    anni
    -0.06
    POSITIVE LOGITS
    sembl
    0.09
    aged
    0.08
    åıĬåħ¶
    0.08
    agens
    0.07
    whose
    0.07
    hood
    0.07
    ä¸Ĭè¿ĩ
    0.07
     ëĮĢìĥģìľ¼ë¡ľ
    0.07
    _authenticated
    0.06
    客ä½ĵ
    0.06
    Activations Density 0.824%

    No Known Activations