© 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. 63211
    Prev
    Next
    INDEX
    Explanations

    event before receive

    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
    orre
    -0.08
    ç¥Ŀ
    -0.07
    å¡ŀ
    -0.07
    beg
    -0.07
     urmÄĥ
    -0.07
    ombs
    -0.07
    ARGS
    -0.07
    ä¸Ĭæ·»
    -0.07
    apiro
    -0.06
    éħį
    -0.06
    POSITIVE LOGITS
     vice
    0.08
    两èĢħ
    0.08
    ÛĴ
    0.07
    ITOR
    0.07
     intim
    0.07
    upp
    0.07
    两èĢħçļĦ
    0.06
    erg
    0.06
    itaire
    0.06
    æĺ¯åħ¶
    0.06
    Activations Density 0.024%

    No Known Activations