© 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. 46669
    Prev
    Next
    INDEX
    Explanations

    suggests that

    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
    Äįko
    -0.09
     ÐĴÑģÑĤÑĢе
    -0.08
     ÐŁÐ¾Ñģко
    -0.08
     Сооб
    -0.08
     (!((
    -0.08
    aday
    -0.07
     ÐŁÐ¾Ð¿ÑĢо
    -0.07
    धà¥įय
    -0.07
    eration
    -0.07
    ä¸ŃåĽ½å®¶
    -0.07
    POSITIVE LOGITS
    ively
    0.10
     forth
    0.10
    've
    0.09
    forth
    0.08
    iveness
    0.08
     rằng
    0.08
    entially
    0.08
    ungsweise
    0.07
     bahwa
    0.07
    ed
    0.07
    Activations Density 0.021%

    No Known Activations