© 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. 33148
    Prev
    Next
    INDEX
    Explanations

    programming keywords

    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
    jadi
    -0.08
     rede
    -0.08
    ussen
    -0.07
    ispo
    -0.07
    rive
    -0.07
    adian
    -0.07
    åĬłåĭĴ
    -0.07
    spar
    -0.07
    è¿Ľè¡Įè°ĥæķ´
    -0.07
     Roose
    -0.06
    POSITIVE LOGITS
    urah
    0.07
    ãĥķãĥª
    0.07
    çĢļ
    0.07
    éļ¾
    0.07
    ä½łä¹Ł
    0.07
    ä¸įæķ£
    0.07
    åįķåŃIJ
    0.07
    å¾Ĺ
    0.07
    ç»ħ
    0.06
    ATCH
    0.06
    Activations Density 0.240%

    No Known Activations