© 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. 42347
    Prev
    Next
    INDEX
    Explanations

    angular momentum, acoustic attenuation, constant problem

    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
    çŀ¥
    -0.08
    croft
    -0.07
    _bio
    -0.07
    çļĦ交æµģ
    -0.07
    èĥº
    -0.07
    ä¸įæį¢
    -0.07
    igre
    -0.07
    icto
    -0.07
    çģ«çĪĨ
    -0.07
    æ·ĺ
    -0.07
    POSITIVE LOGITS
    ibern
    0.08
    Bundle
    0.08
     bundle
    0.07
    è¹
    0.07
     Couch
    0.07
    æĿŁ
    0.07
    窩
    0.07
     tensor
    0.07
     energy
    0.07
     Sew
    0.07
    Activations Density 0.003%

    No Known Activations