© 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. 10540
    Prev
    Next
    INDEX
    Explanations

    both ... and

    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
    หà¸Ļึà¹Īà¸ĩà¹ĥà¸Ļ
    -0.08
    èĩ³å°ij
    -0.07
    èĩ³å°ijè¦ģ
    -0.07
    å°ijãģªãģıãģ¨ãĤĤ
    -0.07
    spath
    -0.07
    erva
    -0.07
    entral
    -0.07
    addir
    -0.06
    alfa
    -0.06
    shire
    -0.06
    POSITIVE LOGITS
    大åı¯
    0.08
     lẫn
    0.08
    ór
    0.07
    æĪij们èĩªå·±
    0.07
    .integer
    0.07
    mile
    0.07
    à¸Ĺีà¹Ģà¸Ķียว
    0.07
     sowohl
    0.07
    inton
    0.07
    级çļĦ
    0.07
    Activations Density 0.177%

    No Known Activations