© 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. 30136
    Prev
    Next
    INDEX
    Explanations

    Sophus library names

    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
    ï¼Ī
    -0.07
    ä½ľä¸ºä¸Ģç§į
    -0.06
    主
    -0.06
    çĭ¬
    -0.06
    è¶ħ
    -0.06
    Ùħر
    -0.06
    è¶ģ
    -0.06
    etta
    -0.06
    åIJ§
    -0.06
    SC
    -0.06
    POSITIVE LOGITS
    微信æī«ä¸Ģæī«
    0.11
    èѬå¦Ĥ
    0.09
    æ¯Ķå¦Ĥåľ¨
    0.09
    èĢģæŧå°ıåĮº
    0.09
     SimpleName
    0.08
    èque
    0.08
    .debian
    0.08
    ety
    0.08
    ç¾İ丽乡æĿij
    0.08
    æ²¹çĽIJ
    0.08
    Activations Density 0.304%

    No Known Activations