© 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. 46847
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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
    pere
    -0.07
    ront
    -0.06
    cera
    -0.06
     Campan
    -0.06
     PSG
    -0.06
     mẻ
    -0.06
    ä¸Ģè§Ĵ
    -0.06
    ên
    -0.06
     vedi
    -0.06
    UK
    -0.06
    POSITIVE LOGITS
    ede
    0.08
    人以ä¸ĭ
    0.07
    aml
    0.07
    ipse
    0.07
    ä¸ī两
    0.07
    ussy
    0.07
    æ¸
    0.07
    ç´Ģ
    0.07
    ultipart
    0.07
    ellone
    0.06
    Activations Density 0.006%

    No Known Activations