© 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. 39026
    Prev
    Next
    INDEX
    Explanations

    multiple choice, regression, sequence, sclerosis, access

    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
    æĬĺä¸į
    -0.08
    ernen
    -0.08
    à¸Ļาม
    -0.07
    اء
    -0.07
    ninger
    -0.07
    %X
    -0.07
    گاÙĩ
    -0.07
    =-=-=-=-
    -0.07
    osti
    -0.07
    =-=-=-=-=-=-=-=-
    -0.07
    POSITIVE LOGITS
     cạn
    0.07
    æ´ģ
    0.07
    lover
    0.06
    oid
    0.06
    ä½ı宿费
    0.06
    íĻĢ
    0.06
    hey
    0.06
    lok
    0.06
    UIS
    0.06
    ized
    0.06
    Activations Density 0.008%

    No Known Activations