© 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. 49109
    Prev
    Next
    INDEX
    Explanations

    extended free trials

    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
    æŃ£å¦Ĥ
    -0.08
    arina
    -0.08
    FetchRequest
    -0.08
    arana
    -0.07
    å°±å¦Ĥ
    -0.07
    zilla
    -0.07
     Niest
    -0.07
    alborg
    -0.07
    OldData
    -0.07
    -Allow
    -0.07
    POSITIVE LOGITS
     ÑıкобÑĭ
    0.09
    ä»Ģä¹ĪçļĦ
    0.08
     ÙĪØ£ÙĨÙĩ
    0.08
     seien
    0.07
    ulai
    0.07
    å¾Ĺ好
    0.07
    æĶ¹
    0.07
     непÑĢеменно
    0.06
    æŁIJæŁIJ
    0.06
    ...',
    0.06
    Activations Density 0.046%

    No Known Activations