© 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. 61635
    Prev
    Next
    INDEX
    Explanations

    percentage of

    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
    rie
    -0.07
    zens
    -0.07
    æĽ´å¤ļçļĦ
    -0.06
    kena
    -0.06
    edef
    -0.06
    urr
    -0.06
    indy
    -0.06
    brief
    -0.06
    ä¿Ń
    -0.06
    æĶĢæ¯Ķ
    -0.06
    POSITIVE LOGITS
    ä»Ģä¹ĪçļĦ
    0.09
    OnError
    0.08
    ipan
    0.08
    erton
    0.07
    _MARKER
    0.07
    ä¸įåĪ°çļĦ
    0.07
    å·¦åı³çļĦ
    0.07
    whatever
    0.07
    aked
    0.07
    ertain
    0.07
    Activations Density 0.031%

    No Known Activations