© 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. 21620
    Prev
    Next
    INDEX
    Explanations

    factor and multiple of

    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
    åįķèĸĦ
    -0.08
    æĭ©
    -0.08
    综
    -0.07
    åĭ¢
    -0.07
     Stuff
    -0.07
    _defaults
    -0.07
    綾
    -0.07
    شة
    -0.07
    éĩįéĩıè½»
    -0.07
    åī¯åĮºéķ¿
    -0.07
    POSITIVE LOGITS
     division
    0.10
     divisible
    0.09
     divisions
    0.09
    division
    0.09
     Division
    0.09
    åĽłæķ°
    0.08
    æķ´
    0.08
     chia
    0.08
     cleanly
    0.08
     exact
    0.08
    Activations Density 0.010%

    No Known Activations