© 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. 63345
    Prev
    Next
    INDEX
    Explanations

    company, resources, and specific 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
    tsy
    -0.08
    å½Ĵ
    -0.06
    aney
    -0.06
    è°ĥæķ´å¥½
    -0.06
    “
    -0.06
    å½Ĵç»ĵ
    -0.05
    ä¸ĭåIJĮ
    -0.05
     adjusted
    -0.05
    å¦Ĥæŀľä¸į
    -0.05
    å¤į
    -0.05
    POSITIVE LOGITS
    æĪijä¹Łè¦ģ
    0.08
    æī«ä¸Ģæī«
    0.08
    _PIPE
    0.08
    çĤ¹è¿ĻéĩĮ
    0.08
    ãĤĤãģ£ãģ¨
    0.08
    hus
    0.08
    ATEST
    0.08
    æĤ¨çļĦä½įç½®
    0.08
    -done
    0.08
    .predicate
    0.08
    Activations Density 0.192%

    No Known Activations