© 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. 32354
    Prev
    Next
    INDEX
    Explanations

    recipes and DIY projects

    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
    ensee
    -0.06
    æĹłæŃ£å½ĵçIJĨçĶ±
    -0.06
     Maiden
    -0.06
    ä»Ģä¹Īäºĭ
    -0.06
    -ui
    -0.06
    æīĭ段
    -0.06
    çĸijæĥij
    -0.06
     wield
    -0.06
    (NS
    -0.06
     contracts
    -0.06
    POSITIVE LOGITS
    ç®Ģåįķæĺĵ
    0.10
    éĿŀ常ç®Ģåįķ
    0.10
     simples
    0.09
     adaptable
    0.08
    ÃįT
    0.08
    variation
    0.08
     egt
    0.08
     поÑĪа
    0.08
     simple
    0.08
    ä¸ĢæŃ¥
    0.08
    Activations Density 0.336%

    No Known Activations