© 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. 63188
    Prev
    Next
    INDEX
    Explanations

    topics concerning specific subjects

    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
    åľ¨åħ¶ä¸Ń
    -0.07
     accordingly
    -0.07
    ç¸
    -0.06
    è±ģ
    -0.06
    irut
    -0.06
    æ³ŀ
    -0.06
    èħ¾èħ¾
    -0.06
    igel
    -0.06
    æĪijåIJĹ
    -0.06
    ↵
    -0.06
    POSITIVE LOGITS
    è¿Ļç±»
    0.10
    æѤ类
    0.10
    à¹ģà¸ļà¸ļà¸Ļีà¹ī
    0.09
    æŁIJæŁIJ
    0.09
    è¿Ļä¹Ī大
    0.09
     подобного
    0.09
    éĢĻé¡ŀ
    0.08
     ÚĨÙĨÛĮÙĨ
    0.08
    è¿Ļä¹Īç®Ģåįķ
    0.08
    æ¯Ķè¾ĥå¤ļ
    0.08
    Activations Density 0.051%

    No Known Activations