© 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. 26487
    Prev
    Next
    INDEX
    Explanations

    chocolate, sweets, confectionery, desserts

    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
    éĿĴæ¤Ĵ
    -0.08
    çĶŁæ´»æ±¡æ°´
    -0.07
    鱼类
    -0.07
     Dude
    -0.07
     salad
    -0.07
    éĿĴèıľ
    -0.07
    .getElementsByTagName
    -0.07
    客æ°Ķ
    -0.07
     lum
    -0.06
     Jeans
    -0.06
    POSITIVE LOGITS
    çĶľèľľ
    0.10
    ç³ĸæŀľ
    0.09
    åIJ«ç³ĸ
    0.09
     indul
    0.09
     melts
    0.09
    ç³ĸåĪĨ
    0.09
    ç³ĸ
    0.09
     melt
    0.09
    èŀįåĮĸ
    0.09
    çĶľçĤ¹
    0.08
    Activations Density 0.170%

    No Known Activations