© 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. 22263
    Prev
    Next
    INDEX
    Explanations

    programming headers and terms

    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
    reja
    -0.08
    ä¼´
    -0.08
    ய
    -0.08
    ä¼´ä½ł
    -0.07
    iming
    -0.07
    -ex
    -0.07
    祷
    -0.07
    alny
    -0.07
    elter
    -0.07
    esses
    -0.07
    POSITIVE LOGITS
    cook
    0.08
    è§ģ
    0.07
    rote
    0.07
    éĻ£
    0.07
    rop
    0.07
    igor
    0.06
    è¡Įäºĭ
    0.06
    ä¹ı
    0.06
    et
    0.06
    æľīäºĭ
    0.06
    Activations Density 0.422%

    No Known Activations