© 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. 32451
    Prev
    Next
    INDEX
    Explanations

    pseudohalogens, ants, Nazis, original, receptors, gastric, Falls, preacher

    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
    GIO
    -0.07
    *)"
    -0.07
    ç½Ĺæ¹ĸ
    -0.07
    ensk
    -0.07
    ingk
    -0.06
     Hundred
    -0.06
    çľĭæĿ¥
    -0.06
    ieni
    -0.06
    icie
    -0.06
    ׼×ķ׾
    -0.06
    POSITIVE LOGITS
    åħ³éĶ®çݯèĬĤ
    0.08
    èĤĨ
    0.07
    åĴĮæıIJé«ĺ
    0.07
    _snd
    0.07
    è§Ĥåħī
    0.07
    IMA
    0.07
    æĺ¯ä¸Ģ对
    0.07
    ä¸ĢåĢį
    0.07
    èĩŃåij³
    0.06
    ölcs
    0.06
    Activations Density 0.002%

    No Known Activations