© 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. 20333
    Prev
    Next
    INDEX
    Explanations

    numbers or list items

    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
    ä¸īåħ¬
    -0.08
    tu
    -0.07
     hindsight
    -0.07
    ambul
    -0.07
    enia
    -0.06
    æĿ¯æ°´
    -0.06
    éľĵ
    -0.06
    åıªæľīä¸Ģ个
    -0.06
    ç£
    -0.06
    ä½Ĩè¿Ļ
    -0.06
    POSITIVE LOGITS
    à¹Īà¸Ńà¸ĩ
    0.09
    请ä¸İ
    0.08
    æĪijè¦ģè¯Ħ论
    0.07
    æ°Ķæģ¯
    0.07
    åıĬè¦ģæ±Ĥ
    0.07
     overview
    0.07
    aked
    0.07
    ãĤĴãģĭ
    0.07
    see
    0.07
    ä¸ĢèĪ¬éľĢè¦ģ
    0.07
    Activations Density 0.007%

    No Known Activations