© 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. 17334
    Prev
    Next
    INDEX
    Explanations

    web file extensions

    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
    ãĤĤãģ®ãģ§ãģ¯
    -0.08
    ime
    -0.07
    ajan
    -0.07
    æĪijçļĦè¯Ŀ
    -0.07
    ipe
    -0.07
    ope
    -0.06
    éĺħè¯»æľ¬æĸĩåīį
    -0.06
    ©
    -0.06
    é²²
    -0.06
    ä¹±
    -0.06
    POSITIVE LOGITS
    ëģĶ
    0.08
     sic
    0.07
    ÑģовеÑģÑĤ
    0.07
    .gz
    0.07
    лежа
    0.07
    uks
    0.07
    äºİä¸ĸ
    0.07
    referrer
    0.07
     discre
    0.07
    andler
    0.07
    Activations Density 0.093%

    No Known Activations