© 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. 22643
    Prev
    Next
    INDEX
    Explanations

    split into parts or segments

    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
    å¹´ä»ħ
    -0.09
    anyi
    -0.09
    ãĥ³ãĤ¹
    -0.08
    nameof
    -0.08
    åŃ¦æł¡åľ¨
    -0.08
    è¿Ļä»½å·¥ä½ľ
    -0.08
    evol
    -0.08
    िà¤ķा
    -0.08
    _variation
    -0.08
    ä¸ŃåĽ½åľ¨
    -0.08
    POSITIVE LOGITS
    èĭ¥å¹²
    0.09
    /from
    0.08
     two
    0.08
    两éĥ¨åĪĨ
    0.07
    å¦Ĥä¸ĭ
    0.07
    ...
    0.07
     manageable
    0.06
    èĭ¥å¹²ä¸ª
    0.06
    两个
    0.06
    两大类
    0.06
    Activations Density 0.028%

    No Known Activations