© 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. 2513
    Prev
    Next
    INDEX
    Explanations

    equal, similar, comparable, corresponding

    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
    æł¹æľ¬ä¸Ĭ
    -0.08
    æľĢåŁºæľ¬
    -0.07
    .pm
    -0.07
    æľĢæł¹æľ¬
    -0.07
    åľ¨åħ¶ä¸Ń
    -0.06
    åİŁæľ¬çļĦ
    -0.06
    åħ¶ä¸Ńä¸Ģ个
    -0.06
    çİĭåŃIJ
    -0.06
    _subtype
    -0.06
    çļĦæł¹æľ¬
    -0.06
    POSITIVE LOGITS
     altrettanto
    0.10
    亦çĦ¶
    0.09
     igualmente
    0.08
    éĩįè¦ģçļĦæĺ¯
    0.08
    ewn
    0.08
    缸åºĶçļĦ
    0.08
    ondo
    0.08
    éĩıçļĦ
    0.07
     дÑĢÑĥгаÑı
    0.07
    åį³åĪ°
    0.07
    Activations Density 0.180%

    No Known Activations