© 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. 16729
    Prev
    Next
    INDEX
    Explanations

    A -> B -> C -> D

    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
    dir
    -0.07
    严éĩį
    -0.06
    tel
    -0.06
    semb
    -0.06
    illon
    -0.06
    çİĩ
    -0.06
    ç»ıæµİæĬĢæľ¯å¼ĢåıijåĮº
    -0.06
    转è¿ĩ
    -0.06
    为åĩĨ
    -0.06
    å®ŀåĬĽ
    -0.06
    POSITIVE LOGITS
    çĦ¶å¾Į
    0.09
    ASAN
    0.08
     then
    0.08
    ÎŃλ
    0.08
    éĩij森
    0.08
    çļĦæīĢæľīä½ľåĵģ
    0.08
    çĦ¶åIJİæĺ¯
    0.08
    ocken
    0.08
     سپس
    0.08
    ä¸Ģå¸Ĩ
    0.08
    Activations Density 0.009%

    No Known Activations