© 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. 31582
    Prev
    Next
    INDEX
    Explanations

    signatures, colour, photography, fire, season, animation

    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
    ients
    -0.07
    åħ¸
    -0.06
    è¡Įèĩ³
    -0.06
    ÙĪÙħÙĩ
    -0.06
    ceased
    -0.06
    éķIJ
    -0.06
    onus
    -0.05
    stract
    -0.05
    å±ħå¤ļ
    -0.05
    æħ£
    -0.05
    POSITIVE LOGITS
     ës
    0.08
    æĬĬåŃ¦ä¹ł
    0.08
     Jep
    0.07
     fName
    0.07
    åŁł
    0.07
    _dummy
    0.07
    agnol
    0.07
     Away
    0.07
    Ùħاس
    0.07
    ×Ļס
    0.07
    Activations Density 0.074%

    No Known Activations