© 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. 13602
    Prev
    Next
    INDEX
    Explanations

    index combinations ij, jk

    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
    æ¸ħæµģ
    -0.07
    ê¸ī
    -0.07
    å½Ĵç»ĵ
    -0.06
    uis
    -0.06
    иж
    -0.06
    ë°±
    -0.06
     HACK
    -0.06
    isar
    -0.06
    dn
    -0.06
    oph
    -0.06
    POSITIVE LOGITS
    è´
    0.08
    åīįç½®
    0.07
    äºĭåĬ¡
    0.07
    outil
    0.07
    _Syntax
    0.07
    æĺ¯ä½łçļĦ
    0.07
    æŁĦ
    0.07
    .ie
    0.07
    /entity
    0.06
    ÙĥرÙĬ
    0.06
    Activations Density 0.002%

    No Known Activations