© 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. 62452
    Prev
    Next
    INDEX
    Explanations

    choroidal melanoma, /local data, duodenal lesions, unified memory, pars plana, -based studio, OTTs, three dimensions, metre air

    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
    æľªåľ¨
    -0.08
    åħĪåľ¨
    -0.08
    åĤį
    -0.07
    ä¸įèĥ½åľ¨
    -0.07
    æµ·å¤ĸ
    -0.07
    åľĥ
    -0.06
    åĽĽæµ·
    -0.06
    åIJİèĩ³
    -0.06
    ehl
    -0.06
    åŃĺåĤ¨åľ¨
    -0.06
    POSITIVE LOGITS
    icola
    0.10
    ihat
    0.08
    ameda
    0.08
    ä¸ĬçļĦ
    0.08
    ìĹIJìĦľìĿĺ
    0.07
    å¤ĦçļĦ
    0.07
    çļĦå±ħæ°ij
    0.07
    -based
    0.07
    éĤ£è¾¹çļĦ
    0.07
    -mounted
    0.07
    Activations Density 0.208%

    No Known Activations