© 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. 9790
    Prev
    Next
    INDEX
    Explanations

    mathematical or technical terms

    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
    æľīä½Ļ
    -0.07
    _Common
    -0.07
    ;base
    -0.07
    æ±ĤçŁ¥
    -0.07
    交åıīè·¯åı£
    -0.06
    اÙģت
    -0.06
    éĥ½å¼Ģå§ĭ
    -0.06
     phu
    -0.06
    åħ±åIJĮ为
    -0.06
     retard
    -0.06
    POSITIVE LOGITS
    ÃŃv
    0.08
    armi
    0.08
    orza
    0.07
     $\
    0.07
    ÅĤos
    0.07
    ieves
    0.07
     coordin
    0.07
    adge
    0.07
    onto
    0.07
     tame
    0.07
    Activations Density 0.098%

    No Known Activations