© 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. 49939
    Prev
    Next
    INDEX
    Explanations

    satisfying conditions or requests

    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
    er
    -0.09
    erop
    -0.09
    umph
    -0.09
    ovor
    -0.09
    zerű
    -0.08
    orton
    -0.08
    zuge
    -0.08
    ortable
    -0.08
    pio
    -0.08
    alize
    -0.08
    POSITIVE LOGITS
    ä¸įäºĨ
    0.09
    æĿ¡ä»¶çļĦ
    0.09
    ably
    0.08
    以ä¸ĭæĿ¡ä»¶
    0.08
    ment
    0.08
     conditions
    0.08
    ingly
    0.07
     Ñģобой
    0.07
    ness
    0.07
     mãn
    0.07
    Activations Density 0.020%

    No Known Activations