© 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. 62111
    Prev
    Next
    INDEX
    Explanations

    of the

    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
     infatti
    -0.08
    ÑĬÑĤ
    -0.07
    éĩijåŁİ
    -0.06
    ниÑıÑĤ
    -0.06
    ä¹ĭ以
    -0.06
    dessen
    -0.06
    yv
    -0.06
    åģļçļĦå°±æĺ¯
    -0.06
    ãģĮãģĤãģ£ãģ¦
    -0.06
     indeed
    -0.06
    POSITIVE LOGITS
    ewnÄĻ
    0.09
    ä¸ĭåIJĮ
    0.08
    izr
    0.07
    ponsored
    0.07
    ikota
    0.07
    æĹ¥æ¸¸
    0.07
    åĬłåħ¥æĶ¶èĹı
    0.07
    жаÑħ
    0.07
    à¦¿à¦ľ
    0.07
    好åij¢
    0.07
    Activations Density 0.919%

    No Known Activations