© 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. 24102
    Prev
    Next
    INDEX
    Explanations

    flow and spread

    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
    ä¸Ģå¸Ĩé£İ顺
    -0.08
    æĶ¾é£ŀ
    -0.07
    ä¸Ģ鸣
    -0.07
    çĶľé£Ł
    -0.07
    evin
    -0.07
    ä¹ĭäºī
    -0.07
    dep
    -0.07
    åħ±å¤Ħ
    -0.07
    heel
    -0.07
    ounce
    -0.07
    POSITIVE LOGITS
    ĽĦ
    0.08
    å®Ľèĭ¥
    0.08
     Ñģловно
    0.08
    å¼ĢæĿ¥
    0.07
    å°±åĥıæĺ¯
    0.07
    æ¯ıä¸Ģ个è§ĴèIJ½
    0.07
    è¶ĬæĿ¥è¶Ĭ大
    0.07
    èĢĮä¸ĭ
    0.07
    ä¸Ģéģĵéģĵ
    0.07
    åıijæĮ¥çĿĢ
    0.07
    Activations Density 0.105%

    No Known Activations