© 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. 39465
    Prev
    Next
    INDEX
    Explanations

    object/class definitions

    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
    俱ä¹IJéĥ¨
    -0.07
    моÑĤ
    -0.06
    ammel
    -0.06
    oming
    -0.06
    лли
    -0.06
    ãĥIJãĥĪãĥ«
    -0.06
    æĭīçļĦ
    -0.06
    äs
    -0.06
    fatt
    -0.06
    ardin
    -0.06
    POSITIVE LOGITS
    ฯ
    0.08
    æĸ¹æĸ¹éĿ¢
    0.08
    \_
    0.08
    opedia
    0.08
    à¸ģารà¸ĵà¹Į
    0.07
    OrNil
    0.07
    åŃIJæĽ°
    0.07
    æ°ı
    0.07
    iore
    0.07
    ï½ŀãĢį
    0.07
    Activations Density 0.177%

    No Known Activations