© 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. 4800
    Prev
    Next
    INDEX
    Explanations

    role of stigma

    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
    Negative Logits
    尿裤
    -0.07
    Ø©
    -0.07
    é«ĺåıij
    -0.06
     bı
    -0.06
    ublic
    -0.06
    )':
    -0.06
    FLAG
    -0.06
    å°ıäºĮ
    -0.06
    è·ĥ
    -0.06
     Washing
    -0.06
    POSITIVE LOGITS
    lek
    0.08
    andang
    0.08
    alama
    0.08
     Motto
    0.08
    å¼Ģæĭį
    0.08
    æ¾İ
    0.08
    yak
    0.08
    odic
    0.07
    oyer
    0.07
    ç»Ļä½łä¸Ģ个
    0.07
    Activations Density 0.001%

    No Known Activations