© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30488
    Prev
    Next
    INDEX
    Explanations

    math expressions and formulas

    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
    orig
    -0.06
    è¿ĩå±±
    -0.06
    ikian
    -0.06
    æľīè°ģ
    -0.06
    utzen
    -0.06
    常常
    -0.06
    è§Ħå®ļçļĦåħ¶ä»ĸ
    -0.06
    åįİ强
    -0.06
     rarely
    -0.06
    POSE
    -0.06
    POSITIVE LOGITS
    amol
    0.08
    æ¯Ķä¾ĭ
    0.08
    lett
    0.08
     Zy
    0.07
     hectic
    0.07
     boils
    0.07
    åĬłåħ³æ³¨
    0.07
    yty
    0.07
     Kane
    0.07
    pit
    0.07
    Activations Density 0.028%

    No Known Activations