© 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. 27588
    Prev
    Next
    INDEX
    Explanations

    words/tokens after specific words

    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
    udd
    -0.08
    ujud
    -0.07
     thru
    -0.07
    zana
    -0.07
    Dependencies
    -0.07
    £¼
    -0.07
    大åħ´
    -0.07
    举èĩ³
    -0.07
    éĢıæĶ¯
    -0.07
    á»Ļc
    -0.07
    POSITIVE LOGITS
    arium
    0.08
    acher
    0.08
    仪
    0.08
     pragma
    0.07
    ä¸ĥéĩĮ
    0.07
    ç¼Ģ
    0.07
    uckle
    0.07
    æĭīéĩĮ
    0.07
    å·ĿåĮº
    0.07
    halt
    0.07
    Activations Density 0.003%

    No Known Activations