© 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. 31456
    Prev
    Next
    INDEX
    Explanations

    identifies, carries, chooses, selects

    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
    对äºİä¸Ģ个
    -0.07
    ê¶ģ
    -0.07
    对äºİä¸ĢäºĽ
    -0.07
    pum
    -0.06
    ä¸Ģ段æŶéĹ´
    -0.06
     someone
    -0.06
    AME
    -0.06
    æİĤ
    -0.06
    à´ķàµįà´ķ
    -0.06
    çIJĨæĥ³çļĦ
    -0.06
    POSITIVE LOGITS
    ä¸įäºĨ
    0.11
    ä¸įäºĨçļĦ
    0.09
    nable
    0.08
    ä¸įäºĨå¤ļä¹ħ
    0.08
    bable
    0.08
     inev
    0.08
    _PS
    0.08
    {{{
    0.08
    asel
    0.08
     frustra
    0.07
    Activations Density 0.828%

    No Known Activations