© 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. 7096
    Prev
    Next
    INDEX
    Explanations

    peace of mind

    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
    _EXTERN
    -0.09
    ×Ļס
    -0.08
    åĮ£
    -0.08
    ิà¹Īà¸ĩ
    -0.08
    æij©
    -0.08
    æĿijæĿij
    -0.07
    åıİ
    -0.07
    ieder
    -0.07
    olla
    -0.07
     kraf
    -0.07
    POSITIVE LOGITS
    è¯ļå¿ĥ
    0.06
    ä¸ĩåħĥ人æ°ijå¸ģ
    0.06
     Garland
    0.06
    ÑģÑĤÑĥпа
    0.06
    yas
    0.06
    yh
    0.06
    ape
    0.06
    atra
    0.06
    Prem
    0.06
    aka
    0.06
    Activations Density 1.062%

    No Known Activations