© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 40414
    Prev
    Next
    INDEX
    Explanations

    proofs, theorems, and facts

    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
    è³ĵ
    -0.08
     пÑĢикоÑĢ
    -0.08
    ewise
    -0.07
    _MIX
    -0.07
    ä¸įæŶ
    -0.07
    让æĪijçļĦ
    -0.07
    为æĤ£èĢħ
    -0.07
    æľīçĹħ
    -0.07
    åİ»ä½ķ
    -0.07
    è¯ħ
    -0.07
    POSITIVE LOGITS
     famously
    0.10
    çļĦè¯ģæĺİ
    0.08
     famous
    0.08
    çļĦä¼Łå¤§
    0.07
     axiom
    0.07
     proof
    0.07
    åįĥåı¤
    0.07
     traditionally
    0.07
     Cant
    0.07
     foundational
    0.07
    Activations Density 0.037%

    No Known Activations