© 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. 39706
    Prev
    Next
    INDEX
    Explanations

    selective, CRM, calf, Seattle, IB, Leg, Sym, ap

    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
    atak
    -0.07
    ��
    -0.06
    iÄĩ
    -0.06
    ersp
    -0.06
    Agr
    -0.06
    rano
    -0.06
    andinav
    -0.06
    iaux
    -0.06
    æĨ
    -0.06
    alker
    -0.06
    POSITIVE LOGITS
     sonstige
    0.10
     thereof
    0.09
    æĮĸæİĺåħ¬åı¸
    0.09
     ÑģобÑģÑĤвенно
    0.09
    åħ¶ä»ĸçļĦ
    0.08
    顾åIJįæĢĿ
    0.08
    æĺ¯ä½ķåIJ«ä¹ī
    0.08
    ä¸İä¹ĭ
    0.08
    çĽ¸å¯¹åºĶçļĦ
    0.08
    ä»»ä½ķåħ¶ä»ĸ
    0.08
    Activations Density 0.310%

    No Known Activations