© 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. 3977
    Prev
    Next
    INDEX
    Explanations

    name suffix/prefix

    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
    æļĹ示
    -0.06
     y
    -0.06
    æĹłæŃ¢å¢ĥ
    -0.06
    autant
    -0.06
     Means
    -0.06
    书ä¸ŃçļĦ
    -0.06
    è®®
    -0.06
    ä¸ŃçļĦä¸Ģç§į
    -0.06
    足以
    -0.06
    æĦıåij³
    -0.06
    POSITIVE LOGITS
    缮åīįå·²ç»ı
    0.09
    俨çĦ¶
    0.09
    ä¹ĭæīĢ以
    0.08
    éĽĨåħ¨
    0.08
     verfü
    0.08
     insomma
    0.08
    hado
    0.08
    èĻ½çĦ¶æĺ¯
    0.08
    æĹłçĸijæĺ¯
    0.08
    èĻ½çĦ¶åľ¨
    0.08
    Activations Density 0.515%

    No Known Activations