© 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. 39690
    Prev
    Next
    INDEX
    Explanations

    eating and consuming

    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
    å¾Ĵ
    -0.08
    aix
    -0.07
    åĩºå¥ĩ
    -0.07
    åĩºè·¯
    -0.07
    åĩºå¢ĥ
    -0.07
    ä¹°èıľ
    -0.07
     punching
    -0.07
    æ´Ĺè¡£æľį
    -0.07
    ç¼ĸåĪ¶
    -0.07
    åĩ¡äºĭ
    -0.07
    POSITIVE LOGITS
    åĴ½
    0.11
    津津æľīåij³
    0.10
    æ¶ĪåĮĸ
    0.10
     consumption
    0.10
    大åı£
    0.09
    两åı£
    0.09
    æ®ĭ渣
    0.09
    consum
    0.08
    éĩı大
    0.08
     enjoyment
    0.08
    Activations Density 0.081%

    No Known Activations