© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 25091
    Prev
    Next
    INDEX
    Explanations

    America, flies, entrepreneurs

    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
     Bret
    -0.08
    chema
    -0.07
    elib
    -0.07
    igue
    -0.07
    åįĬåľº
    -0.07
    ongi
    -0.07
    (fabs
    -0.07
     اÙĦØŃرارÙĬØ©
    -0.07
    éľ²çıł
    -0.07
    erp
    -0.07
    POSITIVE LOGITS
    对æĸ¹å½ĵäºĭ人
    0.07
    åįģäºĮæĿ¡
    0.06
    zana
    0.06
    zas
    0.06
     gat
    0.06
    å¤ļå±Ĥ
    0.06
     multipart
    0.06
    оÑģÑĤа
    0.06
    ties
    0.06
    heimer
    0.06
    Activations Density 0.007%

    No Known Activations