© 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. 1572
    Prev
    Next
    INDEX
    Explanations

    seem to or sounds like

    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
    ÎŃα
    -0.08
    æį®ç»Łè®¡
    -0.08
    eley
    -0.08
    bruck
    -0.08
    ero
    -0.08
    keh
    -0.08
    osz
    -0.07
    oblin
    -0.07
    øk
    -0.07
    icismo
    -0.07
    POSITIVE LOGITS
     intent
    0.06
     hụt
    0.06
    èªŀ
    0.06
    èĪµ
    0.06
    Results
    0.06
     lastIndex
    0.06
    #$
    0.06
    пÑĢавлениÑı
    0.06
    aut
    0.06
    phasis
    0.06
    Activations Density 0.022%

    No Known Activations