© 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. 63311
    Prev
    Next
    INDEX
    Explanations

    six years years

    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
    _IOC
    -0.08
    ç¿ł
    -0.08
    اص
    -0.07
    akov
    -0.07
    Æ¡n
    -0.07
    upert
    -0.07
    kiye
    -0.07
    #undef
    -0.07
    _CR
    -0.07
    ÙĦاÙģ
    -0.07
    POSITIVE LOGITS
    ickets
    0.06
    ¿
    0.06
    .Encoding
    0.06
    olan
    0.06
    §
    0.06
     бÑİÑĢо
    0.06
     Mala
    0.06
    顺å¿ĥ
    0.06
    ixo
    0.06
    adrat
    0.06
    Activations Density 0.024%

    No Known Activations