© 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. 22994
    Prev
    Next
    INDEX
    Explanations

    fifth degree polynomial

    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
    PTY
    -0.09
    ench
    -0.08
    _CONSOLE
    -0.08
    AFX
    -0.08
    åĨįè§ģ
    -0.07
    ÙĪرÙĬد
    -0.07
    ropa
    -0.07
    é¼İé¼İ
    -0.07
    å¿ĺä¸įäºĨ
    -0.07
    ptions
    -0.07
    POSITIVE LOGITS
    öt
    0.08
    leton
    0.07
    YO
    0.07
    èī²
    0.06
    ä»ĬæĹ¥
    0.06
    ier
    0.06
     vel
    0.06
    ieri
    0.06
    -level
    0.06
    æľĢè¿ij
    0.06
    Activations Density 0.059%

    No Known Activations