© 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. 12357
    Prev
    Next
    INDEX
    Explanations

    light rays path tracing

    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
    è¶ģ
    -0.07
    ç«ĭåį³çĶ³è¯·
    -0.07
    veau
    -0.06
    å±±åľ°
    -0.06
    æĢ»è®¡
    -0.06
    æĹ¶æľŁçļĦ
    -0.06
    åī¯
    -0.06
    æ¹ĺ
    -0.06
    æĭĨ
    -0.06
    çĶŁãģ¾ãĤĮ
    -0.06
    POSITIVE LOGITS
     paths
    0.08
    istar
    0.08
     rays
    0.08
     intercepted
    0.08
    åĢ
    0.07
    दा
    0.07
     path
    0.07
    çļĦè¿ij
    0.07
    解æĥij
    0.07
    è·¯å¾Ħ
    0.07
    Activations Density 0.006%

    No Known Activations