© 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. 30371
    Prev
    Next
    INDEX
    Explanations

    systems, applications, internet, abuse

    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
    人åħ¬
    -0.07
    åŃIJäºĨ
    -0.07
    å¯ĩ
    -0.06
    »
    -0.06
    转åŀĭåıijå±ķ
    -0.06
    ilight
    -0.06
    заÑħ
    -0.06
    äºĨåIJ§
    -0.06
    plin
    -0.06
    roat
    -0.06
    POSITIVE LOGITS
     also
    0.13
     ÙĩÙħÚĨÙĨÛĮÙĨ
    0.11
    ä¹ŁåĽłæѤ
    0.11
     inoltre
    0.11
     therefore
    0.11
     ÑĤакже
    0.10
    also
    0.10
     itself
    0.09
     furthermore
    0.09
     ALSO
    0.09
    Activations Density 0.283%

    No Known Activations