© 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. 38950
    Prev
    Next
    INDEX
    Explanations

    mail it / CT scans / bays / video clips / waits / collect items / principal members

    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
    以æѤ
    -0.07
    목
    -0.07
    æį®æѤ
    -0.07
    osci
    -0.07
    اتÙĩا
    -0.06
    agger
    -0.06
    åľ¨åįĬ
    -0.06
    %i
    -0.06
     Eins
    -0.06
    Ùģت
    -0.06
    POSITIVE LOGITS
     inilah
    0.09
    ãģ¨ãģĦãģ£ãģ¦ãĤĤ
    0.08
    ucker
    0.08
     menda
    0.08
    ĥģ
    0.08
    对人çļĦ
    0.08
    å°±æĺ¯æĪij们çļĦ
    0.07
     altså
    0.07
     Caro
    0.07
     infatti
    0.07
    Activations Density 0.006%

    No Known Activations