© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 15173
    Prev
    Next
    INDEX
    Explanations

    older adults, irreducible, rural PWID

    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
    cant
    -0.06
    veda
    -0.06
    aland
    -0.06
    æĺĬ
    -0.06
    alai
    -0.06
    #.
    -0.06
     chant
    -0.06
    è¿Ļç§įæĸ¹æ³ķ
    -0.06
    obl
    -0.06
    èĻ½çĦ¶çİ°åľ¨
    -0.06
    POSITIVE LOGITS
    unar
    0.08
    dade
    0.08
    iminal
    0.07
    elder
    0.07
    ittel
    0.07
    æĢ»ä½ĵ
    0.07
    çļĦæĹ¥æľ¬
    0.07
    ç«ĭç§ĭ
    0.07
    .python
    0.07
    è¯ģæį®è¯ģæĺİ
    0.07
    Activations Density 0.039%

    No Known Activations