© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 9521
    Prev
    Next
    INDEX
    Explanations

    mathematical and scientific text sections

    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
     subt
    -0.06
     fict
    -0.06
    è¶ĭ
    -0.06
     ste
    -0.06
    asco
    -0.06
     pron
    -0.06
     relationship
    -0.06
    主次
    -0.06
    alz
    -0.06
    缸æĴŀ
    -0.06
    POSITIVE LOGITS
    unic
    0.09
    çļĦæŃĮ
    0.09
    ấy
    0.09
    æľŁæ»¡
    0.08
    ihad
    0.08
    大æĬĬ
    0.08
     Canta
    0.08
     Фло
    0.08
    æ¹§
    0.08
    reens
    0.08
    Activations Density 0.004%

    No Known Activations