© 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. 26182
    Prev
    Next
    INDEX
    Explanations

    salt and seasoning

    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
     subur
    -0.07
    _testing
    -0.07
    Ñģпен
    -0.07
    天éŃĶ
    -0.07
    éĿ¢ç§¯è¾¾
    -0.07
    æĿĤ交
    -0.07
    ecom
    -0.07
    mö
    -0.07
    -Class
    -0.06
    anches
    -0.06
    POSITIVE LOGITS
    çĽIJ
    0.10
     salt
    0.10
     Salt
    0.09
    åĴ¸
    0.09
    é£ŁçĽIJ
    0.09
    Salt
    0.09
    salt
    0.08
     taste
    0.08
    é¹½
    0.08
    çĽIJåĴĮ
    0.08
    Activations Density 0.015%

    No Known Activations