© 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. 51024
    Prev
    Next
    INDEX
    Explanations

    may or might followed by verbs

    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
    ugins
    -0.07
    ãĤ»ãĤ¹
    -0.07
    ì¢
    -0.07
    ROY
    -0.07
    æĺİæĺİ
    -0.07
    <|repo_name|>
    -0.07
    ãģĻãĤĭãģ¨
    -0.07
    طب
    -0.07
    uelle
    -0.07
    太好äºĨ
    -0.07
    POSITIVE LOGITS
    ma
    0.07
    issy
    0.07
    abh
    0.07
    ES
    0.06
    abit
    0.06
    íĺijìĿĺ
    0.06
    iefer
    0.06
    ire
    0.06
    åĮĢ称
    0.06
    obile
    0.06
    Activations Density 0.092%

    No Known Activations