© 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. 19518
    Prev
    Next
    INDEX
    Explanations

    with respect to

    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
    ÑĢина
    -0.07
     complain
    -0.07
    å¨ħ
    -0.07
     ún
    -0.06
    饱满çļĦçĥŃæĥħ
    -0.06
    縱
    -0.06
    TestId
    -0.06
    绣ä¸Ģéĥ¨ç½²
    -0.06
    _RESERVED
    -0.06
    INGTON
    -0.06
    POSITIVE LOGITS
    æĦıæĢĿæĺ¯
    0.07
    encil
    0.07
    agna
    0.07
    ader
    0.07
    èĢģå¸Ī说
    0.07
    awas
    0.07
    说å®ŀè¯Ŀ
    0.07
    çļĦæĦıæĢĿæĺ¯
    0.07
    ilen
    0.07
    arness
    0.07
    Activations Density 0.062%

    No Known Activations