© 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. 55654
    Prev
    Next
    INDEX
    Explanations

    ways to do something

    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
    åĪ©
    -0.06
    å¦ĤåIJĮ
    -0.06
    åį³
    -0.06
    èµ
    -0.06
    reh
    -0.06
    åĨħ
    -0.06
    è¶Ĭ
    -0.06
    imming
    -0.06
     Consequently
    -0.06
     equivalent
    -0.05
    POSITIVE LOGITS
     tampoco
    0.09
    ãģĵãĤĮãĤĤ
    0.09
     ÑĤоже
    0.09
    ä¹Łä¸įè¡Į
    0.09
    ä¹Łä¸įéĶĻ
    0.09
    éĶ¦æ¶Ľ
    0.09
    лÑĮкÑĥ
    0.08
    ãĥ¼ãĥģ
    0.08
    ÑĭÑĢ
    0.08
    arkin
    0.08
    Activations Density 0.010%

    No Known Activations