© 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. 15449
    Prev
    Next
    INDEX
    Explanations

    the following word

    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
    åıijçĶŁäºĭæķħ
    -0.07
    æĥ³å¾ĹåĪ°
    -0.07
     Einschrän
    -0.07
    esson
    -0.06
    eon
    -0.06
    ÃijA
    -0.06
    accia
    -0.06
    _parms
    -0.06
     caff
    -0.06
    IOC
    -0.06
    POSITIVE LOGITS
    esso
    0.07
    ä¼Ĺ
    0.07
     aforementioned
    0.07
    thouse
    0.07
    ç»Ļ大家æݨèįIJ
    0.06
    ópolis
    0.06
    åį«ä¸ľ
    0.06
    å½ĵ家
    0.06
    веÑĢо
    0.06
    æĹłå¤Ħä¸įåľ¨
    0.06
    Activations Density 0.505%

    No Known Activations