© 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. 3509
    Prev
    Next
    INDEX
    Explanations

    create programs

    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
     zbog
    -0.07
    æĶ¶éĽĨçļĦ
    -0.07
     aufgrund
    -0.07
    çĶ±äºİåħ¶
    -0.07
     due
    -0.07
    æĿ¥ä¸´ä¹ĭéĻħ
    -0.07
    åıªåĽł
    -0.07
     dank
    -0.07
    due
    -0.07
     additionally
    -0.07
    POSITIVE LOGITS
    uron
    0.08
    设计åĩº
    0.08
    åĪ¶å®ļåĩº
    0.07
    pins
    0.07
    æĹ¢åı¯
    0.07
    या
    0.07
    æĹ¢èĥ½
    0.07
    istes
    0.07
     coherent
    0.07
     personalized
    0.07
    Activations Density 0.187%

    No Known Activations