© 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. 23675
    Prev
    Next
    INDEX
    Explanations

    conditional approval or subject to conditions

    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
    мп
    -0.07
    ีà¹Īยว
    -0.07
    è¶ĭåĬ¿
    -0.07
    æĮĩåįĹ
    -0.07
    ä½ķå¿ħ
    -0.07
    ä¸į足
    -0.07
    odyn
    -0.07
    ÐĺÐIJ
    -0.06
    igon
    -0.06
    writes
    -0.06
    POSITIVE LOGITS
    æĿ¡ä»¶çļĦ
    0.15
     conditions
    0.14
    æĿ¡ä»¶æĺ¯
    0.14
    æĿ¡ä»¶åĴĮ
    0.14
    æĿ¡ä»¶
    0.14
    conditions
    0.14
     condition
    0.13
     Conditions
    0.13
     conditional
    0.13
    æ¢Ŀ件
    0.13
    Activations Density 0.086%

    No Known Activations