© 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. 9068
    Prev
    Next
    INDEX
    Explanations

    deprecated code or errors

    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
    erus
    -0.08
    çĶ³æĬ¥è¡¨
    -0.08
    äg
    -0.07
    ächt
    -0.07
    arus
    -0.07
    å°Ĩè¾¾
    -0.07
    ä¹Łåĥı
    -0.07
    èijī
    -0.07
    bö
    -0.07
    ationToken
    -0.07
    POSITIVE LOGITS
    çģµå±±
    0.08
    ahui
    0.07
    åĴĮä¿¡æģ¯
    0.07
    ale
    0.06
    onte
    0.06
    fri
    0.06
    æĿŀ
    0.06
    meta
    0.06
     Cata
    0.06
    åĴĮ社ä¼ļåıijå±ķ
    0.06
    Activations Density 1.108%

    No Known Activations