© 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. 34311
    Prev
    Next
    INDEX
    Explanations

    on the ground or floor

    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
     internal
    -0.09
    åħ§éĥ¨
    -0.08
    bilt
    -0.08
    å¸Ĩ
    -0.08
     Internal
    -0.08
    æĮĤ
    -0.08
    åij¼åķ¸
    -0.08
    åĨħéĥ¨
    -0.08
     hung
    -0.08
    æĮĤåľ¨
    -0.08
    POSITIVE LOGITS
    éĵº
    0.16
    éĭª
    0.14
    éĵºè®¾
    0.14
    éĵºåŀ«
    0.13
     ground
    0.11
    æķ£èIJ½
    0.11
    åľ¨åľ°ä¸Ĭ
    0.11
     groundwork
    0.11
    åľ°æ¯¯
    0.11
    ground
    0.10
    Activations Density 0.247%

    No Known Activations