© 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. 14969
    Prev
    Next
    INDEX
    Explanations

    need 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
    ìķ¼
    -0.10
    ãģ¾ãģ¾
    -0.08
    å·²æľī
    -0.08
    amaha
    -0.07
    anca
    -0.07
     gern
    -0.07
    acking
    -0.07
     gerne
    -0.07
    å¤ļ彩
    -0.07
    å¿ħè¦ģæŶ
    -0.07
    POSITIVE LOGITS
    ï¸ı
    0.09
     to
    0.08
    lessly
    0.08
    å°Ķå¤ļ
    0.08
    Ø©
    0.08
    çļĦæĸ¹æ³ķæĿ¥
    0.08
    æŶéĹ´æĿ¥
    0.08
    entially
    0.07
    à¨Ĥ
    0.07
    't
    0.07
    Activations Density 0.072%

    No Known Activations