© 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. 28555
    Prev
    Next
    INDEX
    Explanations

    signals describing

    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
    alia
    -0.07
    prd
    -0.07
    ummings
    -0.07
    PRI
    -0.07
    çĶŁæ´»ä¼ļ
    -0.07
    ä¸Ĭå½ĵ
    -0.07
    _marker
    -0.07
    ATOR
    -0.07
    èľ¿
    -0.06
    æīĵæĿ¥
    -0.06
    POSITIVE LOGITS
    åĵ
    0.08
    otte
    0.08
    ç¾½
    0.08
    ảo
    0.07
    ä¸įå¦Ĥ
    0.07
    arty
    0.07
    æĹłçĥŁ
    0.07
    ubu
    0.07
    à¸Ńรà¹Į
    0.07
     Embassy
    0.07
    Activations Density 0.028%

    No Known Activations