© 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. 43557
    Prev
    Next
    INDEX
    Explanations

    “

    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
    -away
    -0.08
    ldb
    -0.07
    ä¹ĭæĺŁ
    -0.07
    å¹´èĩ³ä»Ĭ
    -0.07
    lot
    -0.07
    Sexy
    -0.07
     exclusively
    -0.07
    èĩªè¾¾
    -0.07
    ×ķ×ķ
    -0.07
     neighb
    -0.07
    POSITIVE LOGITS
    ¹
    0.08
    zung
    0.07
     Dorf
    0.07
    ä¸īéĩĮ
    0.06
    igor
    0.06
    åľ¨æĹ¥å¸¸
    0.06
    åIJĮæŶè¿ĺ
    0.06
    ½
    0.06
    اع
    0.06
    iphy
    0.06
    Activations Density 0.045%

    No Known Activations