© 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. 12726
    Prev
    Next
    INDEX
    Explanations

    lobes, lobulated, lip, be, bi-lobe

    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
    agara
    -0.07
    åħ¬ç¤º
    -0.07
    建
    -0.07
    å¾·åŁº
    -0.07
    å·¡
    -0.07
    æķ£
    -0.07
    ä¸ĭ
    -0.07
     ÐijÑĥдÑĥ
    -0.07
    第åįģä¸Ģ
    -0.07
    失
    -0.07
    POSITIVE LOGITS
    çĬ¶çļĦ
    0.07
    -shaped
    0.07
    çĶ¨æĪ·ä½¿çĶ¨
    0.07
    å¤ĸéĥ¨çݯå¢ĥ
    0.07
    hati
    0.07
    lette
    0.06
    ezza
    0.06
    beutel
    0.06
    SHOT
    0.06
    æľ¬åºĹ
    0.06
    Activations Density 0.002%

    No Known Activations