© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 41819
    Prev
    Next
    INDEX
    Explanations

    conditional criteria

    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
    pus
    -0.07
    ä¹ĭéķ¿
    -0.06
    pline
    -0.06
    auté
    -0.06
     Zam
    -0.06
    ê´´
    -0.06
    宿
    -0.06
     existente
    -0.06
    éĽıå½¢
    -0.06
    uit
    -0.06
    POSITIVE LOGITS
     criteria
    0.13
     criterion
    0.13
    criteria
    0.12
    çŃĽéĢī
    0.12
     criter
    0.11
     Criterion
    0.11
     Criteria
    0.11
    篩
    0.11
    _criteria
    0.11
    çŃĽ
    0.11
    Activations Density 0.056%

    No Known Activations