© 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. 29706
    Prev
    Next
    INDEX
    Explanations

    minimizing, formulating, skin, ending, assessing, maintaining, determining

    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
    Ñħам
    -0.08
    epen
    -0.07
     Potr
    -0.07
     neod
    -0.07
     Hodg
    -0.07
    ä¸ĸçķĮä¸ĬæľĢ大çļĦ
    -0.07
    çĥŃåįĸ
    -0.07
    ehlen
    -0.07
    roda
    -0.07
    aler
    -0.07
    POSITIVE LOGITS
    /manage
    0.07
    è±ĨèħIJ
    0.07
     unwanted
    0.07
    ¢
    0.07
    atoon
    0.06
    çļĦéĩįè¦ģæīĭ段
    0.06
    ĩ
    0.06
    osis
    0.06
    ÑĤиÑİ
    0.06
    åĴĮæıIJé«ĺ
    0.06
    Activations Density 0.069%

    No Known Activations