© 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. 28573
    Prev
    Next
    INDEX
    Explanations

    category names

    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
    ÑĩÑĮ
    -0.09
    inox
    -0.08
    ċ
    -0.08
     prezi
    -0.08
     lẫn
    -0.08
     adel
    -0.08
    åı¯ä»¥æ»¡è¶³
    -0.07
    chartInstance
    -0.07
    umn
    -0.07
    éĶ¦æ¶Ľ
    -0.07
    POSITIVE LOGITS
    ZZ
    0.08
    æľ¬é¢ĺ
    0.08
    åŁºç¡ĢçŁ¥è¯Ĩ
    0.07
    缸åħ³çŁ¥è¯Ĩ
    0.07
    åŁºæľ¬çŁ¥è¯Ĩ
    0.07
    çķ¥
    0.07
    çŁ¥è¯ĨçĤ¹
    0.07
    èĢĥæŁ¥
    0.06
    åĩ¡
    0.06
    书åIJ§
    0.06
    Activations Density 0.005%

    No Known Activations