© 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. 29124
    Prev
    Next
    INDEX
    Explanations

    French names

    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
    OfType
    -0.08
    å¦ĤåĪĿ
    -0.08
    UGE
    -0.08
    king
    -0.08
    ingue
    -0.08
     Cummings
    -0.07
    phu
    -0.07
    ÛĮØ´
    -0.07
    Bindings
    -0.07
    kers
    -0.07
    POSITIVE LOGITS
    ä¸Ģä½ĵ
    0.06
    ItemCount
    0.06
    åİĨéĻ©
    0.06
    ffffffff
    0.06
     اÙĦساØŃ
    0.06
    æl
    0.06
     fend
    0.06
    åİĨ
    0.06
    ÑĤÑĭ
    0.06
    oleans
    0.05
    Activations Density 0.015%

    No Known Activations