© 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. 64992
    Prev
    Next
    INDEX
    Explanations

    Gita and Maharshi

    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
    opedia
    -0.10
    spur
    -0.08
    æİĸ
    -0.08
    æĦŁæŁĵçļĦ
    -0.08
    aiser
    -0.07
    å¾ĺ
    -0.07
    ievi
    -0.07
    åĴĢ
    -0.07
    æĦŁæŁĵ
    -0.07
    valuator
    -0.07
    POSITIVE LOGITS
    æĶ¶ç¼´
    0.07
    öl
    0.07
    ìĦ¸
    0.07
    avad
    0.06
    ali
    0.06
    Speech
    0.06
     hij
    0.06
    æĺ¯å¯¼èĩ´
    0.06
    ee
    0.06
     Yoga
    0.06
    Activations Density 0.002%

    No Known Activations