© 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. 23518
    Prev
    Next
    INDEX
    Explanations

    substitution for parameters

    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
    æľīç¥ŀ
    -0.08
    abia
    -0.07
    olia
    -0.06
    attel
    -0.06
     accidental
    -0.06
    è¿ĩç¥ŀ
    -0.06
     rud
    -0.06
    äºĭå®ŀåĴĮ
    -0.06
    è®°å½ķäºĨ
    -0.06
    aios
    -0.06
    POSITIVE LOGITS
     substitute
    0.10
    æ¶Ī
    0.09
     substitution
    0.09
     Substitute
    0.08
     substituted
    0.08
     substit
    0.08
     substitutes
    0.08
    -Smith
    0.08
    æķ´ä¸ªä¸ĸçķĮ
    0.08
    çŁ¥æĥħ
    0.07
    Activations Density 0.003%

    No Known Activations