© 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. 24598
    Prev
    Next
    INDEX
    Explanations

    end punctuation

    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
    etting
    -0.08
    ashing
    -0.07
    å¦ĤæŃĮ
    -0.07
     Inherits
    -0.07
    idane
    -0.07
    avo
    -0.07
    odor
    -0.06
    orr
    -0.06
    æķ°æ¬¡
    -0.06
     Twice
    -0.06
    POSITIVE LOGITS
    ®
    0.08
    luck
    0.08
    éb
    0.07
    à¸Ķย
    0.07
     übrigens
    0.07
    forg
    0.07
    åħ¬
    0.07
    åı¦å¤ĸè¿ĺæľī
    0.07
    åı¯ä¾Ŀ
    0.07
    ÑĻе
    0.06
    Activations Density 0.176%

    No Known Activations