© 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. 55064
    Prev
    Next
    INDEX
    Explanations

    accurate assessment

    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
    jenigen
    -0.11
    zelf
    -0.10
    ality
    -0.10
    itters
    -0.09
    oret
    -0.09
    egen
    -0.09
    ÙĬاÙĨ
    -0.08
    tlement
    -0.08
     акÑĤивноÑģÑĤи
    -0.08
    strand
    -0.08
    POSITIVE LOGITS
    æĹłè¯¯
    0.12
    idental
    0.09
    itude
    0.09
     Äijắn
    0.08
    -ish
    0.08
    zza
    0.08
    èµ·è§ģ
    0.08
    à¹ģมà¹Īà¸Ļยำ
    0.07
    ndern
    0.07
    identally
    0.07
    Activations Density 0.019%

    No Known Activations