© 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. 34881
    Prev
    Next
    INDEX
    Explanations

    cyrillic characters following `maka` or `č`

    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
    REEN
    -0.09
    eram
    -0.09
    yani
    -0.09
    bolo
    -0.09
    erber
    -0.09
    ambre
    -0.08
    erma
    -0.08
    ãĥ³
    -0.08
    pital
    -0.08
     orto
    -0.08
    POSITIVE LOGITS
    éĹ®é¢ĺæĿ¥äºĨ
    0.12
    adays
    0.09
    ingly
    0.08
    że
    0.08
    æĹıèĩªæ²»
    0.07
    麽
    0.07
    ager
    0.07
    upon
    0.07
    fois
    0.07
    åĽŀäºĭ
    0.06
    Activations Density 0.001%

    No Known Activations