© 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. 60111
    Prev
    Next
    INDEX
    Explanations

    Roman numeral kings and names

    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
    Not in Any Lists

    No Comments

    Negative Logits
    atch
    -0.07
    ely
    -0.07
    丼çĶŁ
    -0.06
    леÑģ
    -0.06
    åIJĦèī²
    -0.06
    éĤ£è¾¹çļĦ
    -0.06
    代代
    -0.06
    åİĨ
    -0.06
    çĶŁäºĨ
    -0.06
    åłķ
    -0.06
    POSITIVE LOGITS
    妮
    0.08
    çĶ²çĬ¶
    0.08
    antom
    0.08
    ìĨĶ
    0.08
    *)"
    0.08
     Sexo
    0.07
     Tér
    0.07
    åŃĿå¿ĥ
    0.07
    ertest
    0.07
    uncan
    0.07
    Activations Density 0.095%

    No Known Activations