© 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. 62868
    Prev
    Next
    INDEX
    Explanations

    governance, risk, and compliance

    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
    åŃĺåĤ¨æľįåĬ¡
    -0.08
    conte
    -0.08
     tar
    -0.08
    оби
    -0.08
    缸åħ³æ³ķå¾ĭ责任
    -0.08
    ä¿¡æģ¯åĴ¨è¯¢
    -0.07
     dolg
    -0.07
    .getLocal
    -0.07
    çĵ¦
    -0.07
    é¡·
    -0.07
    POSITIVE LOGITS
    åĨħéĥ¨æݧåĪ¶
    0.10
     audit
    0.09
     Audit
    0.09
    Audit
    0.09
     controls
    0.09
    éĺ²èĮĥ
    0.08
    å¤įæł¸
    0.08
     oversight
    0.08
    æµģç¨ĭ
    0.08
    audit
    0.08
    Activations Density 0.020%

    No Known Activations