© 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. 51011
    Prev
    Next
    INDEX
    Explanations

    because, when, if, case

    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
    anc
    -0.06
     اج
    -0.06
    aine
    -0.06
    اÙĨÙĬØ©
    -0.06
    lish
    -0.06
    ãĥĵãĥ³
    -0.06
    contr
    -0.06
    .cycle
    -0.06
    æĹłè¾ľ
    -0.06
    cab
    -0.06
    POSITIVE LOGITS
    æī¾ä¸įåĪ°
    0.14
    æĹłæ³ķ
    0.13
    à¹Ħมà¹Īสามารà¸ĸ
    0.11
    缺ä¹ı
    0.11
    æĹłæ³ķ满足
    0.11
    æĺ¯æĹłæ³ķ
    0.11
    æĿ¥ä¸įåıĬ
    0.11
    çĦ¡æ³ķ
    0.11
     inability
    0.11
     unable
    0.11
    Activations Density 0.402%

    No Known Activations