© 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. 40614
    Prev
    Next
    INDEX
    Explanations

    wholesale, companies, Netanya, Viagra, car, account, POV, phone

    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
    ieras
    -0.07
    ogan
    -0.07
    ^{
    -0.07
    åģļæ³ķ
    -0.07
    Deal
    -0.07
    ...**
    -0.07
    جرد
    -0.06
     fov
    -0.06
    æ°Ľ
    -0.06
    çļĦåģļæ³ķ
    -0.06
    POSITIVE LOGITS
    åīįåįģåIJį
    0.08
    åĵ¥ä¼¦
    0.08
    åįģ大
    0.07
    icolo
    0.07
     ê²°ë¡ł
    0.07
    好ä¸ĢçĤ¹
    0.07
     Led
    0.07
    æľ¬æĸĩå°Ĩ
    0.06
    adc
    0.06
    çĥģ
    0.06
    Activations Density 0.233%

    No Known Activations