© 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. 61452
    Prev
    Next
    INDEX
    Explanations

    followed by punctuation or specific words

    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
    enko
    -0.07
    éĿŀåħ¬
    -0.07
    +x
    -0.06
    ãĥįãĥ«
    -0.06
    代ä¹ĭ
    -0.06
    èĭ¦è¾£
    -0.06
    icar
    -0.06
    羣å®ŀæĢ§è´Łè´£
    -0.06
    ä¿Ŀéļľå·¥ä½ľ
    -0.06
    bow
    -0.06
    POSITIVE LOGITS
    éĿĴé¾Ļ
    0.08
    ØŃÙĦ
    0.07
    çİĦæѦ
    0.07
    ÑĸÑı
    0.07
    semble
    0.07
    åIJ¸æĶ¶
    0.07
    Æ¯ÆłNG
    0.07
    Ùijت
    0.07
    ascin
    0.07
     SetValue
    0.07
    Activations Density 0.001%

    No Known Activations