© 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. 47343
    Prev
    Next
    INDEX
    Explanations

    rules, limitations, exceptions, provisions

    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
    Needed
    -0.08
    insic
    -0.07
    为ä»Ģä¹Īä¼ļ
    -0.07
    reas
    -0.07
    iscard
    -0.07
    æİĪæĿĥèĮĥåĽ´åĨħ使çĶ¨
    -0.07
    expected
    -0.07
    ñado
    -0.07
    _expected
    -0.07
    yasi
    -0.07
    POSITIVE LOGITS
    è§Ħå®ļäºĨ
    0.12
    è§Ħå®ļ
    0.11
    éĢĤçĶ¨èĮĥåĽ´
    0.11
    çļĦè§Ħå®ļ
    0.10
     provisions
    0.10
    æĺİç¡®è§Ħå®ļ
    0.10
    éĢĤçĶ¨
    0.09
     expressly
    0.09
    缸åħ³è§Ħå®ļ
    0.09
    ä¸Ģå¾ĭ
    0.09
    Activations Density 0.059%

    No Known Activations