© 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. 38085
    Prev
    Next
    INDEX
    Explanations

    percentage or 100%

    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
    psilon
    -0.07
    ëĭ¥
    -0.06
    PropertyDescriptor
    -0.06
    ably
    -0.06
    åı¯éĿł
    -0.06
     responsibly
    -0.06
    afil
    -0.06
    overs
    -0.06
    æīĢåѦä¸ĵä¸ļ
    -0.06
    erias
    -0.06
    POSITIVE LOGITS
    为åįķä½į
    0.11
    为æłĩåĩĨ
    0.10
    设为
    0.10
    é»ĺ认
    0.10
    åŁºåĩĨ
    0.10
    å®ļ为
    0.09
    datum
    0.09
    benchmark
    0.09
    ä¸ºéĽ¶
    0.09
    engel
    0.09
    Activations Density 0.039%

    No Known Activations