© 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. 8974
    Prev
    Next
    INDEX
    Explanations

    from ... to

    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
    idor
    -0.08
    odin
    -0.07
    еÑĤÑĢо
    -0.07
    åĤ¨
    -0.07
    áĥĺáĥĹ
    -0.07
    urit
    -0.07
    onale
    -0.07
    Persistence
    -0.07
    inox
    -0.07
     viper
    -0.07
    POSITIVE LOGITS
    转åıĺ为
    0.10
    被åĬ¨
    0.09
    éĢIJæ¸IJæĪIJ为
    0.09
    åįķ纯çļĦ
    0.09
    åıĺ为
    0.09
    åĨįåĪ°
    0.08
    åįķ纯
    0.08
     merely
    0.08
     becoming
    0.08
    çİ°åľ¨å¼Ģå§ĭ
    0.08
    Activations Density 0.038%

    No Known Activations