© 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. 8998
    Prev
    Next
    INDEX
    Explanations

    formula syntax

    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
    ئ
    -0.07
    obia
    -0.07
    带äºĨ
    -0.07
    aranya
    -0.07
    AccessException
    -0.07
    urun
    -0.07
    èĥ³
    -0.07
    afir
    -0.06
    ëł¹
    -0.06
    ocker
    -0.06
    POSITIVE LOGITS
    usp
    0.07
     Bene
    0.07
    ·
    0.07
    inete
    0.07
    жиÑĤ
    0.07
    ond
    0.06
    è·Į
    0.06
    åĴĮ好
    0.06
    imest
    0.06
    ì§ģ
    0.06
    Activations Density 0.004%

    No Known Activations