© 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. 1359
    Prev
    Next
    INDEX
    Explanations

    physicist, Tesla, Musk, Wheeler

    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
    preter
    -0.09
    isci
    -0.08
    xAA
    -0.08
    ffy
    -0.08
    ,start
    -0.08
    onta
    -0.08
    ×ķ×Ŀ
    -0.08
    eldom
    -0.08
    GRAM
    -0.08
    agma
    -0.08
    POSITIVE LOGITS
    å½ĵæŶçļĦ
    0.07
    以å¾ħ
    0.07
    æĥ³å¾Ĺ
    0.07
    å½ĵæŶ
    0.07
    åľ¨å½ĵæŶ
    0.07
     physicists
    0.06
     physicist
    0.06
     proposal
    0.06
    éĤ£æŶåĢĻ
    0.06
    astro
    0.06
    Activations Density 0.008%

    No Known Activations