© 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. 13002
    Prev
    Next
    INDEX
    Explanations

    X-ray spectroscopy

    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
    enzi
    -0.07
    æ£
    -0.07
    undra
    -0.07
    åıĺéĩıçļĦ
    -0.07
    çļĭ
    -0.06
    ç»ĵåĨ°
    -0.06
    ucin
    -0.06
    æĬ
    -0.06
     river
    -0.06
    ç¥ģ
    -0.06
    POSITIVE LOGITS
    lectron
    0.09
     ÑĢенÑĤ
    0.09
    igraf
    0.08
     emitted
    0.08
    åIJĪéĩij
    0.08
     shielding
    0.08
    ocaust
    0.08
     electron
    0.08
    ç©´
    0.08
     atomic
    0.08
    Activations Density 0.018%

    No Known Activations