© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 33130
    Prev
    Next
    INDEX
    Explanations

    antenna pairs forming

    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
    åĽ¢ä½ĵ
    -0.07
    uentes
    -0.07
    egan
    -0.07
    ç§ĭæľĪ
    -0.07
    ocab
    -0.07
    ابÙĦ
    -0.07
    ULE
    -0.07
     Gelt
    -0.07
    quip
    -0.07
    ipas
    -0.07
    POSITIVE LOGITS
    ahir
    0.08
    istu
    0.08
    igi
    0.07
    åħģ
    0.07
    çļĦè¿Ļç§į
    0.07
    _compare
    0.07
    äºĮè¿ŀ
    0.07
    ighb
    0.07
    æŃ¤èµ·å½¼
    0.06
    缸éĤ»
    0.06
    Activations Density 0.135%

    No Known Activations