© 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. 4611
    Prev
    Next
    INDEX
    Explanations

    technical lists and extensions

    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
    æĶ¯æı´
    -0.07
    è½®
    -0.07
     Mut
    -0.07
    çĥĪ
    -0.06
    好
    -0.06
    arez
    -0.06
     comp
    -0.06
    æĸĩåĮĸä¸Ńå¿ĥ
    -0.06
    aurus
    -0.06
    ©
    -0.06
    POSITIVE LOGITS
    實é«Ķ
    0.10
    人æĿIJ
    0.09
     payloads
    0.09
    maz
    0.08
     CONTENT
    0.08
     å®ŁéļĽãģ«
    0.08
    physical
    0.08
    èĤīä½ĵ
    0.08
    köz
    0.08
    è¡ĢèĤī
    0.08
    Activations Density 0.743%

    No Known Activations