© 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. 3224
    Prev
    Next
    INDEX
    Explanations

    lung cancer therapy

    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
    é
    -0.07
    aja
    -0.06
    æ½ľ
    -0.06
     appunto
    -0.06
     غÙĬرÙĩ
    -0.06
     Anat
    -0.06
    æĥ³åĪ°è¿ĻéĩĮ
    -0.06
    bst
    -0.06
      ↵
    -0.06
     vol
    -0.06
    POSITIVE LOGITS
    ãģĵãģ¡ãĤīãĤĤ
    0.16
    ãģĵãĤĮãĤĤ
    0.13
    again
    0.13
     again
    0.12
     опÑıÑĤÑĮ
    0.10
     Again
    0.10
    åIJĮæł·
    0.10
    Again
    0.10
    åIJĮæł·æĺ¯
    0.09
     ebenfalls
    0.09
    Activations Density 0.126%

    No Known Activations