© 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. 56697
    Prev
    Next
    INDEX
    Explanations

    code, technical terms

    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
    è§Ī
    -0.06
    éļıçĿĢå¹´é¾Ħ
    -0.06
    åıijæĮ¥åĩº
    -0.06
    avers
    -0.06
    /release
    -0.06
     Patterson
    -0.06
    aky
    -0.06
    æĹłæŶæĹłåĪ»
    -0.06
    åĦĴ
    -0.06
     throughout
    -0.06
    POSITIVE LOGITS
    á»ijn
    0.09
     induk
    0.09
    ewe
    0.08
    idik
    0.08
    omatik
    0.08
     обÑĢазова
    0.08
    ẹo
    0.08
    æŃ¤æ¬¡
    0.08
    ênh
    0.08
     booked
    0.07
    Activations Density 0.003%

    No Known Activations