© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48701
    Prev
    Next
    INDEX
    Explanations

    dark

    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
    iasco
    -0.11
    estro
    -0.09
    ียà¸ĩ
    -0.09
    yled
    -0.08
    erator
    -0.08
    alcon
    -0.08
    ardy
    -0.08
    variably
    -0.08
     bơ
    -0.08
    umer
    -0.08
    POSITIVE LOGITS
    ened
    0.12
    สà¸Ļิà¸Ĺ
    0.11
    æ²īæ²ī
    0.10
    ness
    0.10
    ening
    0.10
    é»ijçļĦ
    0.09
    (er
    0.09
    /black
    0.08
    ç¨ĭ度
    0.08
    ç¨ĭ度ä¸Ĭ
    0.08
    Activations Density 0.027%

    No Known Activations