© 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. 12206
    Prev
    Next
    INDEX
    Explanations

    "

    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
    ovac
    -0.08
    åģıåģı
    -0.08
    еÑī
    -0.07
    usche
    -0.07
    inga
    -0.07
    _PHYS
    -0.07
     biz
    -0.07
    ÙĪØ©
    -0.07
    西山
    -0.06
    è²
    -0.06
    POSITIVE LOGITS
     ople
    0.07
     appos
    0.06
    kada
    0.06
    λεÏĥμα
    0.06
     Sandy
    0.06
    ongen
    0.06
    asan
    0.06
    æ±°
    0.06
    apé
    0.06
    综ä¸ĬæīĢè¿°
    0.06
    Activations Density 0.005%

    No Known Activations