© 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. 62667
    Prev
    Next
    INDEX
    Explanations

    names and places

    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
    idet
    -0.09
    Ãłng
    -0.08
    stek
    -0.08
    ãģľ
    -0.07
    qn
    -0.07
    ritis
    -0.07
    ijnen
    -0.07
    åİ
    -0.07
    Administration
    -0.07
    olis
    -0.07
    POSITIVE LOGITS
     indirectly
    0.08
    èĻ½çĦ¶ä¸įæĺ¯
    0.08
     ÑģоÑĩеÑĤ
    0.07
    åħĪä»İ
    0.07
    åħ¼
    0.07
    äºĴåĬ¨
    0.07
    ä¸İ人
    0.07
    ç»ĵåIJĪ
    0.07
     combine
    0.07
    aul
    0.07
    Activations Density 0.342%

    No Known Activations