© 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. 16319
    Prev
    Next
    INDEX
    Explanations

    author names

    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
    çķ
    -0.07
    èī°
    -0.07
    عد
    -0.07
    ê±´
    -0.06
     ìĭ±
    -0.06
    æ¯Ķäºļ
    -0.06
    AAP
    -0.06
    å¢Ĵ
    -0.06
    LIN
    -0.06
    enuity
    -0.06
    POSITIVE LOGITS
    sov
    0.07
    ÙĤض
    0.07
    åıįè¦Ĩ
    0.07
    иÑĤÑĥ
    0.07
    ités
    0.06
    tmpl
    0.06
    à¸ķà¹Ī
    0.06
    vinc
    0.06
    Ñģек
    0.06
    jsc
    0.06
    Activations Density 0.064%

    No Known Activations