© 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. 56274
    Prev
    Next
    INDEX
    Explanations

    it is

    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
    ural
    -0.08
     terj
    -0.08
    jakan
    -0.07
    ä¸ºæľŁ
    -0.07
    ÑĢенÑĮ
    -0.07
     succesfully
    -0.07
    ullet
    -0.07
    umper
    -0.07
    ãģĭãģ¯
    -0.07
    ständig
    -0.07
    POSITIVE LOGITS
     therefore
    0.07
     particularly
    0.07
     perhaps
    0.07
     however
    0.07
     now
    0.07
    particularly
    0.07
    ä¸įéĢı
    0.06
    æѤæŶçļĦ
    0.06
     imagine
    0.06
    alik
    0.06
    Activations Density 1.940%

    No Known Activations