© 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. 30343
    Prev
    Next
    INDEX
    Explanations

    Which what

    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
    immel
    -0.07
    æ³Ĭ车
    -0.06
     content
    -0.06
     bro
    -0.06
    ikan
    -0.06
    ust
    -0.06
     bl
    -0.06
    zin
    -0.06
     super
    -0.06
    æľī为
    -0.06
    POSITIVE LOGITS
    æĽ´æĸ°æŶéĹ´
    0.09
    磼
    0.08
    ắp
    0.08
    eof
    0.08
    ادÙĨ
    0.08
    æĸ°çĶŁæ´»
    0.07
    aliases
    0.07
    áĢĸáĢ¼
    0.07
    equality
    0.07
    Õ¸ÖĢ
    0.07
    Activations Density 0.001%

    No Known Activations