© 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. 9558
    Prev
    Next
    INDEX
    Explanations

    examples, estimates, purposes, informational

    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
    å°±æĺ¯æĪij们çļĦ
    -0.08
    راج
    -0.07
    å¼ĥæĿĥ
    -0.07
    анда
    -0.07
     Ply
    -0.07
    å¹²èĦĨ
    -0.07
    ç½®ä¹ĭ
    -0.07
     impun
    -0.07
    æĺ¾å¾ĹæĽ´åĬł
    -0.07
    hower
    -0.07
    POSITIVE LOGITS
    ãģĤãģı
    0.12
    ä»ħä¾ĽåıĤèĢĥ
    0.09
    ä»ħ为
    0.08
    ä»ħä½ľ
    0.08
     illustr
    0.08
    ä»ħæĺ¯
    0.08
    ä¸į代表
    0.08
    olim
    0.07
    ä»ħ代表
    0.07
    ç»ĿéĿŀ
    0.07
    Activations Density 0.166%

    No Known Activations