© 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. 57529
    Prev
    Next
    INDEX
    Explanations

    most common or basic

    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
    повÑĸ
    -0.09
    åĪ«è¯´
    -0.08
    éĤ£æł·çļĦ
    -0.08
    çļĦéĤ£äºĽ
    -0.08
    atera
    -0.08
    ropole
    -0.08
    çļĦéĤ£ä¸ªäºº
    -0.08
    éĤ£ä»½
    -0.08
    éĤ£äºº
    -0.08
    .pb
    -0.08
    POSITIVE LOGITS
    !
    0.09
    ä¹Łæĺ¯æľĢ
    0.08
    !,
    0.08
    !',
    0.08
    !.
    0.07
     Schultz
    0.07
    ä¸Ģ对
    0.07
    irt
    0.07
    !'
    0.07
     least
    0.07
    Activations Density 0.047%

    No Known Activations