© 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. 3571
    Prev
    Next
    INDEX
    Explanations

    types, variations, or classifications

    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
    íĮħ
    -0.07
    对æīĢ
    -0.07
    å¿ħè¦ģæŶ
    -0.06
    没å¿ħè¦ģ
    -0.06
     заÑĢанее
    -0.06
     Ordin
    -0.06
    fig
    -0.06
    zi
    -0.06
     ideally
    -0.06
    æĸ¤
    -0.06
    POSITIVE LOGITS
    好åĥıæĺ¯
    0.10
    好åĥı
    0.10
    æĪijè®°å¾Ĺ
    0.09
    ä¹Łè¢«ç§°ä¸º
    0.09
     reportedly
    0.09
     sometimes
    0.08
     nowadays
    0.08
     widespread
    0.08
    被人们
    0.08
    sometimes
    0.08
    Activations Density 0.003%

    No Known Activations