© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61793
    Prev
    Next
    INDEX
    Explanations

    .com domains

    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
    ä¸įè¿ľ
    -0.08
     Fraser
    -0.07
    adari
    -0.07
    æĽ´æĸ°æĹ¥æľŁ
    -0.06
    åĬĽä½ľ
    -0.06
    indh
    -0.06
    å¿ĹæĪIJ
    -0.06
    ÑĪÑĤÑĥ
    -0.06
    éģ·
    -0.06
    ajas
    -0.06
    POSITIVE LOGITS
     mismatch
    0.10
    Mismatch
    0.10
    ismatch
    0.09
     mism
    0.08
     Ristor
    0.07
    ambi
    0.07
     similarities
    0.07
    acker
    0.07
     Compare
    0.07
     endings
    0.07
    Activations Density 0.004%

    No Known Activations