© 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. 46917
    Prev
    Next
    INDEX
    Explanations

    ÑįÑĤо blocks

    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
    nya
    -0.10
    ÑģÑı
    -0.09
    jenigen
    -0.09
    ly
    -0.09
    rish
    -0.09
    OperationException
    -0.08
    à¸Ļัà¹īà¸Ļ
    -0.08
    kah
    -0.08
    à¸Ħà¹Į
    -0.08
    dessen
    -0.08
    POSITIVE LOGITS
     also
    0.08
     wÅĤaÅĽnie
    0.07
    warzys
    0.07
    ÑĹ
    0.07
    人æīĢ
    0.07
     either
    0.07
    äººä¹Ł
    0.07
     же
    0.06
    Ò£
    0.06
    ä¸Ģç§į
    0.06
    Activations Density 0.037%

    No Known Activations