© 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. 63158
    Prev
    Next
    INDEX
    Explanations

    unique values or identifiers

    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
    ulu
    -0.07
    ledon
    -0.07
    æľīä½Ļ
    -0.07
    è¿Ļ两ç§į
    -0.07
    asket
    -0.06
    è¿Ļ两
    -0.06
     Whe
    -0.06
    tfoot
    -0.06
    平衡
    -0.06
    置身
    -0.06
    POSITIVE LOGITS
     unique
    0.17
     Unique
    0.16
    Unique
    0.16
     uniqueness
    0.16
    unique
    0.16
     Ñĥника
    0.15
    çĭ¬çī¹
    0.14
    çļĦçĭ¬çī¹
    0.14
    çĭ¬ä¸ĢæĹłäºĮçļĦ
    0.14
     UNIQUE
    0.14
    Activations Density 0.021%

    No Known Activations