© 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. 20655
    Prev
    Next
    INDEX
    Explanations

    higher order

    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
    urit
    -0.09
    西åįĹéĥ¨
    -0.09
    owi
    -0.08
    orman
    -0.08
     anywhere
    -0.08
    å¿«æĬ¥
    -0.08
    åĴĮç»´çĶŁç´ł
    -0.08
    бак
    -0.08
    ably
    -0.08
    izen
    -0.08
    POSITIVE LOGITS
    _than
    0.09
    -than
    0.09
    Than
    0.08
    _THAN
    0.08
     than
    0.08
    æĽ´åħ¨
    0.08
    -order
    0.07
    次çļĦ
    0.07
    als
    0.07
    iore
    0.07
    Activations Density 0.019%

    No Known Activations