© 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. 23937
    Prev
    Next
    INDEX
    Explanations

    if not

    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
    plin
    -0.08
    åıĪåĪ°
    -0.07
    æĹ¥ä»¥æĿ¥
    -0.07
    å¾ĪæĹ©å°±
    -0.07
    ä¹ĭåŃIJ
    -0.07
    byn
    -0.07
    书åIJ§
    -0.07
    ç¬ijè¯Ń
    -0.07
    gies
    -0.07
    Ĺ
    -0.07
    POSITIVE LOGITS
     anybody
    0.08
     conceivable
    0.08
     imaginable
    0.08
    IfExists
    0.08
     anyone
    0.07
     Pera
    0.07
     could
    0.07
    could
    0.07
    -if
    0.07
    ä½łèĥ½
    0.07
    Activations Density 0.333%

    No Known Activations