© 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. 60538
    Prev
    Next
    INDEX
    Explanations

    popular, travelling, affordable

    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
    æ¾İ
    -0.07
    ä»»
    -0.07
    è¿Ļæł·çļĦè¯Ŀ
    -0.07
    æģIJæĢķ
    -0.07
    çļĦè¯Ŀ
    -0.07
    åĽłæ¶īå«Į
    -0.07
    fax
    -0.07
    èĤ¯å®ļæĺ¯
    -0.07
    太å¤ļ
    -0.07
    èĩ³å°ij
    -0.06
    POSITIVE LOGITS
    ä¹Łå°±ä¸į
    0.12
     appunto
    0.09
    ä¹Łå°±
    0.07
    æĢİèĥ½
    0.07
    åıĪå¦Ĥ
    0.07
    à¸Ļัà¹Īà¸Ļà¹Ģà¸Ńà¸ĩ
    0.07
    æĪij们çľĭåĪ°
    0.07
    æīįå¾Ĺ以
    0.07
    ä¹ĥèĩ³
    0.07
    åģļèµ·
    0.07
    Activations Density 0.110%

    No Known Activations