© 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. 16423
    Prev
    Next
    INDEX
    Explanations

    closing punctuation and symbols

    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
    ä¸įæ²»
    -0.07
    .pivot
    -0.07
    è§ģæѤ
    -0.07
    ä¸įæħİ
    -0.07
    upal
    -0.07
    minster
    -0.06
    intai
    -0.06
    ahan
    -0.06
    goo
    -0.06
    hausen
    -0.06
    POSITIVE LOGITS
    Ïĥι
    0.08
    贯穿äºİ
    0.08
    ä¸īåľ°
    0.07
    第ä¸ī款
    0.07
    çī¹æĸ°
    0.07
    åºĶçĶ¨æĬĢæľ¯
    0.07
    éĹ®é¢ĺåĴĮ
    0.07
    -avatar
    0.07
    лон
    0.07
    æĸ¹éĿ¢ä¹Ł
    0.07
    Activations Density 0.066%

    No Known Activations