© 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. 7242
    Prev
    Next
    INDEX
    Explanations

    regime descriptions and method resolution

    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
    isar
    -0.07
    esame
    -0.07
    åѦåĪ¶
    -0.07
    xcc
    -0.07
    osat
    -0.07
    족
    -0.06
    uton
    -0.06
    знаÑĤÑĮ
    -0.06
     Perk
    -0.06
    å¦Ĥ鼨
    -0.06
    POSITIVE LOGITS
    _CODES
    0.07
    brig
    0.07
    ħ§
    0.07
    rie
    0.07
     Chall
    0.07
    loor
    0.07
    æī¿æĭħäºĨ
    0.06
    dere
    0.06
    agne
    0.06
    hdl
    0.06
    Activations Density 0.061%

    No Known Activations