© 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. 61296
    Prev
    Next
    INDEX
    Explanations

    code delimiters and keywords

    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
     à¤Ńर
    -0.08
    ä¸ĬèµĽåŃ£
    -0.08
    epass
    -0.07
    রণ
    -0.07
    PLICATION
    -0.07
     varsa
    -0.07
    æľ¬åľºæ¯ĶèµĽ
    -0.07
    ehold
    -0.07
    çŃĭ
    -0.07
    UnderTest
    -0.07
    POSITIVE LOGITS
    ä½ľ
    0.07
    amica
    0.06
    ãģ¿ãģ«
    0.06
     Isk
    0.06
     Cobb
    0.06
    横è¡Į
    0.06
    ↵
    0.06
    ÙħاÙĦ
    0.06
    æĹħ游æĻ¯åĮº
    0.06
     ID
    0.06
    Activations Density 0.436%

    No Known Activations