© 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. 44749
    Prev
    Next
    INDEX
    Explanations

    binary digits and bases

    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
    #undef
    -0.07
    fert
    -0.07
    ilon
    -0.06
     domest
    -0.06
    haft
    -0.06
    't
    -0.06
    chal
    -0.06
    wi
    -0.06
    ROID
    -0.05
    è¡Į人
    -0.05
    POSITIVE LOGITS
    areth
    0.08
    å¼Ģ头çļĦ
    0.08
     zza
    0.08
    igio
    0.07
    ÃĢN
    0.07
    "]').
    0.07
    ¾¸
    0.07
    esel
    0.07
    [href
    0.07
    erne
    0.07
    Activations Density 0.033%

    No Known Activations