© 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. 41306
    Prev
    Next
    INDEX
    Explanations

    reverse and abstract

    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
    ÑĪип
    -0.07
    onn
    -0.07
    éĶIJ
    -0.06
    à¹Ĥà¸ŀ
    -0.06
    etro
    -0.06
    äºĮåįģä¸ī
    -0.06
     Tenn
    -0.06
    ç¯ĩä¸Ģ
    -0.06
    ä»»ä½ķä¸Ģç§į
    -0.06
    ijk
    -0.06
    POSITIVE LOGITS
    неÑģ
    0.07
    antz
    0.07
    æķ¢äºİ
    0.07
    赶å¿Ļ
    0.07
    åľĪ
    0.07
    人为
    0.07
    erior
    0.07
    -night
    0.07
    ä¸Ģå¤ķ
    0.07
    .ls
    0.07
    Activations Density 0.011%

    No Known Activations