© 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. 34641
    Prev
    Next
    INDEX
    Explanations

    mathematical variables and operations

    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
    -assets
    -0.08
    ernt
    -0.08
    WARD
    -0.08
    ç»İ
    -0.08
    osat
    -0.07
    ward
    -0.07
    illez
    -0.07
    åĩŃèIJ¥ä¸ļæī§çħ§
    -0.07
    飻
    -0.07
    åĴķåĻľ
    -0.07
    POSITIVE LOGITS
    èIJį
    0.07
    éĩı身
    0.06
    '
    0.06
    åĪ¶åº¦çļĦ
    0.06
    缺
    0.06
    km
    0.06
    åŃ£
    0.06
    æĭīå¾·
    0.06
    æ´ŀåı£
    0.06
    pend
    0.06
    Activations Density 0.101%

    No Known Activations