© 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. 2399
    Prev
    Next
    INDEX
    Explanations

    programming language construct

    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
    æĪĸåħ¶
    -0.08
    orit
    -0.07
    è´Łè´£çļĦ
    -0.07
    æķ£åİ»
    -0.07
    á»ħn
    -0.07
    irin
    -0.07
    ä¸ºçĽ®æłĩ
    -0.07
    enheim
    -0.07
    elage
    -0.07
    è´Łè´£å¯¹
    -0.07
    POSITIVE LOGITS
    åľ¨è¿Ļæł·çļĦ
    0.11
    åľ¨è¿Ļç§į
    0.10
    inc
    0.09
     differently
    0.08
     dort
    0.07
     definitions
    0.07
    çŃīåŁºæľ¬
    0.07
    çļĦå®ļä¹ī
    0.07
     Muh
    0.07
    rap
    0.07
    Activations Density 0.140%

    No Known Activations