© 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. 24267
    Prev
    Next
    INDEX
    Explanations

    guess what

    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
    igon
    -0.09
    ament
    -0.08
    ampton
    -0.08
    kot
    -0.08
    ìį¨
    -0.08
    aining
    -0.07
    èĨĢ
    -0.07
     Bein
    -0.07
    ÛĮس
    -0.07
    èĩªå·±çĭ¬çī¹çļĦ
    -0.07
    POSITIVE LOGITS
    ptive
    0.08
    imating
    0.08
    imates
    0.07
    rasil
    0.07
    imate
    0.07
    ãģµãģĨãģ«
    0.07
    umpt
    0.07
    æĥ³çļĦ
    0.07
    æĪIJ羣
    0.07
    ingly
    0.07
    Activations Density 0.025%

    No Known Activations