© 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. 65489
    Prev
    Next
    INDEX
    Explanations

    Background of Related Art

    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
    Õ¸ÖĤÕ¶
    -0.08
    remo
    -0.08
    iong
    -0.07
    itom
    -0.07
    交æīĢ
    -0.07
    åĨħ容æıIJä¾Ľæĸ¹
    -0.07
    iba
    -0.07
    rit
    -0.07
    gd
    -0.07
    obe
    -0.07
    POSITIVE LOGITS
    est
    0.07
    estim
    0.06
     pisc
    0.06
    ujur
    0.06
    eree
    0.06
    lest
    0.06
     IMG
    0.06
    人称
    0.06
    veal
    0.06
    irage
    0.06
    Activations Density 0.001%

    No Known Activations