© 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. 59103
    Prev
    Next
    INDEX
    Explanations

    academic or technical contexts

    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
     lim
    -0.07
    (eventName
    -0.07
    akah
    -0.06
    AGO
    -0.06
    plit
    -0.06
    quanto
    -0.06
    ä½Ļ次
    -0.06
    oon
    -0.06
    (ByVal
    -0.06
     igen
    -0.06
    POSITIVE LOGITS
    ës
    0.08
    StringValue
    0.08
    oure
    0.07
    ä¹ĭç±»çļĦ
    0.07
    esson
    0.07
    лл
    0.07
    åı¯èĥ½å°±
    0.07
    ===========
    0.07
    hort
    0.07
    zimmer
    0.07
    Activations Density 0.001%

    No Known Activations