© 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. 29252
    Prev
    Next
    INDEX
    Explanations

    alphanumeric sequences

    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
    urd
    -0.06
    leter
    -0.06
    æĽ´å¤ļ
    -0.06
    à¸ĺุ
    -0.05
    uppe
    -0.05
    马è¹Ħ
    -0.05
    @gmail
    -0.05
    ¬
    -0.05
     HÆ°á»Ľng
    -0.05
    ãĤĴæĽ´æĸ°
    -0.05
    POSITIVE LOGITS
    çŁ¥éģĵä½ł
    0.08
    ä¾Ľå¤§å®¶
    0.08
    ä¹ĭæĺŁ
    0.08
    ARK
    0.08
    æĪijåIJ§
    0.08
    mios
    0.08
     diserta
    0.08
    æĸĩåĵ²
    0.07
    åķĬåķĬ
    0.07
    nyata
    0.07
    Activations Density 0.188%

    No Known Activations