© 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. 39899
    Prev
    Next
    INDEX
    Explanations

    пÑĢи ved

    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
    ़
    -0.08
    æĸ°åĬłåĿ¡
    -0.08
    วà¸ģ
    -0.07
    оÑĢÑĤа
    -0.07
    èĪ
    -0.06
    é¼İé¼İ
    -0.06
    ussed
    -0.06
    æĹ¶è¾°
    -0.06
    ä½Ĩä¸įéĻIJäºİ
    -0.06
     Guzzle
    -0.06
    POSITIVE LOGITS
    stood
    0.10
     razie
    0.09
     Gelegenheit
    0.08
    ÑĥÑģа
    0.08
    ]*)
    0.08
    tk
    0.08
    bliż
    0.08
    umi
    0.08
    زÙĬ
    0.08
    olica
    0.08
    Activations Density 0.028%

    No Known Activations