© 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. 21223
    Prev
    Next
    INDEX
    Explanations

    is the "I" statement

    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
    éħİ
    -0.07
    strstr
    -0.07
    æĸĻ
    -0.06
    .esp
    -0.06
    åIJĮæĢ§
    -0.06
    åĢ¦
    -0.06
    è¦
    -0.06
    jet
    -0.06
    è´
    -0.06
     fed
    -0.06
    POSITIVE LOGITS
    è¿ĺåı¯ä»¥éĢļè¿ĩ
    0.09
    è¿ĺåĮħæĭ¬
    0.08
    çĶŁæķĪä¹ĭæĹ¥èµ·
    0.08
    æľīä¸ĭåĪĹæĥħå½¢ä¹ĭä¸ĢçļĦ
    0.08
    è¿ĺæľīä¸Ģç§į
    0.08
     alternatively
    0.08
    سÙĬØ©
    0.08
    perator
    0.07
     errorHandler
    0.07
    ä¹Łåı¯ä»¥éĢļè¿ĩ
    0.07
    Activations Density 0.005%

    No Known Activations