© 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. 664
    Prev
    Next
    INDEX
    Explanations

    transmission

    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
    деÑģÑıÑĤ
    -0.11
    íĻĶëIJľ
    -0.09
    idden
    -0.09
     kÄħ
    -0.08
    lick
    -0.08
    ģ
    -0.08
    terapi
    -0.08
    uxtap
    -0.08
    tics
    -0.08
    tober
    -0.08
    POSITIVE LOGITS
    ively
    0.08
    身æķĻ
    0.08
    ix
    0.07
    al
    0.07
    rence
    0.07
    ed
    0.07
    ÑģлÑĮ
    0.07
    oare
    0.07
    าว
    0.07
    家å®Ŀ
    0.07
    Activations Density 0.036%

    No Known Activations