© 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. 46048
    Prev
    Next
    INDEX
    Explanations

    commands and official actions

    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
    å°ıåŃIJ
    -0.07
    URING
    -0.07
    æĶ¯æĴij
    -0.06
    StateException
    -0.06
    åī¯ä¸»å¸Ń
    -0.06
    çĨĻ
    -0.06
    ä½ij
    -0.06
    scha
    -0.06
    æľªæľī
    -0.06
    åIJ¸å¼ķäºĨä¼Ĺå¤ļ
    -0.06
    POSITIVE LOGITS
    åĴĮè¦ģæ±Ĥ
    0.11
    åıĬè¦ģæ±Ĥ
    0.11
    è¦ģæ±ĤåĴĮ
    0.09
    è¦ģæ±Ĥ
    0.09
    è¦ģæ±Ĥåħ¶
    0.09
    ãģ«å¾ĵ
    0.09
    è¦ģæ±Ĥè¿Ľè¡Į
    0.09
    设计è¦ģæ±Ĥ
    0.09
    åij½ä»¤
    0.09
    äºīåģļ
    0.09
    Activations Density 0.116%

    No Known Activations