© 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. 30076
    Prev
    Next
    INDEX
    Explanations

    worldwide, -wide, wide, ally

    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
     ÑĢÑıдÑĥ
    -0.08
    ÙģØ´
    -0.08
    å¸Ĥå§Ķå®£ä¼łéĥ¨
    -0.08
    sov
    -0.08
    son
    -0.08
    æĺ¯æķ´ä¸ª
    -0.07
    éĩįéĩįçļĦ
    -0.07
    æľ¬æ³ķ
    -0.07
    stype
    -0.07
    åŃIJå¼Ł
    -0.07
    POSITIVE LOGITS
    èĮĥåĽ´åĨħ
    0.10
     تÙĤرÙĬب
    0.10
    ä¸ĢçĽĺ
    0.09
    -wide
    0.08
    èĮĥåĽ´åĨħ使çĶ¨
    0.08
    èĮĥåĽ´åĨħçļĦ
    0.08
    åĴĮåĽ½éĻħ
    0.08
    wide
    0.08
    çļĨæľī
    0.08
    except
    0.08
    Activations Density 0.174%

    No Known Activations