© 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. 28664
    Prev
    Next
    INDEX
    Explanations

    code commentslicense headers

    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
     Concept
    -0.07
    anta
    -0.07
    asi
    -0.06
    Concept
    -0.06
    eed
    -0.06
    ¦
    -0.06
    ock
    -0.06
    åħħåĪĨäºĨ解
    -0.06
    ä¹IJ
    -0.06
    èĢģ大
    -0.06
    POSITIVE LOGITS
    ëm
    0.08
    åįİå¾·
    0.08
     farmace
    0.08
    ÑĤÑĮе
    0.08
    Patr
    0.07
    æľ¬é¢ĺçŃĶæ¡Ī
    0.07
    ilers
    0.07
    bih
    0.07
    olley
    0.07
     ÏĢάν
    0.07
    Activations Density 0.005%

    No Known Activations