© 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. 57557
    Prev
    Next
    INDEX
    Explanations

    (x, [n, L, (t

    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
    é¢ĺ为
    -0.07
     ((*
    -0.06
     ((!
    -0.06
    ä¸ĢçıŃ
    -0.06
    åºķä¸ĭçļĦ
    -0.06
    OSE
    -0.06
    ((__
    -0.06
    oseb
    -0.06
    ợ
    -0.06
    à¹ĥ
    -0.06
    POSITIVE LOGITS
    jol
    0.08
    ()
    0.08
    ():
    0.08
    æ´»åĬ¨æŶ
    0.08
    (x
    0.08
    (),
    0.08
    gba
    0.07
    ()][
    0.07
    éģĵåıĭ
    0.07
    (t
    0.07
    Activations Density 0.017%

    No Known Activations