© 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. 21168
    Prev
    Next
    INDEX
    Explanations

    end of statement

    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
    ...',
    -0.09
    æł¹æį®åħ¶
    -0.08
    Ùİات
    -0.07
    mert
    -0.07
    ...",
    -0.07
    _secs
    -0.07
    æĬĬä»ĸçļĦ
    -0.07
    agar
    -0.07
    -0.06
    çıŃçļĦ
    -0.06
    POSITIVE LOGITS
    çļĦè¿ĺæľī
    0.09
    ãĢĤ
    0.07
    åıĪå¦Ĥ
    0.07
     voilÃł
    0.07
    èĢģ人家
    0.07
    )||(
    0.07
    æľīæѤ
    0.07
     ayrıca
    0.06
    åIJĮä¸Ĭ
    0.06
    产åĵģæľįåĬ¡
    0.06
    Activations Density 0.006%

    No Known Activations