© 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. 18806
    Prev
    Next
    INDEX
    Explanations

    marketer, locks, Titanic, axiom, privileged, online, violent

    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
    çī¹å°Ķ
    -0.10
     sequer
    -0.09
     appunto
    -0.08
     ÙĪبÙĬÙĨ
    -0.08
    ä¸į误
    -0.08
    croft
    -0.08
    éĢļåĬĽ
    -0.08
    åĪ°æĻļ
    -0.08
    å®ŀåĪĻ
    -0.08
    åıĸåĨ³
    -0.08
    POSITIVE LOGITS
    åIJĹ
    0.15
    äºĨåIJĹ
    0.12
    æĪijåIJĹ
    0.12
    åĹİ
    0.11
    äºĨåĹİ
    0.09
    äºĨä¹Ī
    0.08
    çļĦåIJĹ
    0.08
     but
    0.08
    ãģĤãĤĬãģ¾ãģĻãģĮ
    0.07
    ãģ¾ãģĽãĤĵãģĮ
    0.07
    Activations Density 1.434%

    No Known Activations