© 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. 64579
    Prev
    Next
    INDEX
    Explanations

    units, currencies, percentages or separators

    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
    强è°ĥçļĦæĺ¯
    -0.06
    A
    -0.06
     %+
    -0.06
    ron
    -0.06
    åıijçİ°èĩªå·±
    -0.06
    nd
    -0.06
    ch
    -0.06
    ***
    -0.06
    ->
    -0.06
     dest
    -0.06
    POSITIVE LOGITS
    åįĥæĸ¹
    0.10
    æĶ¶èĹıæľ¬ç«Ļ
    0.09
    egov
    0.09
    人åħ¬
    0.09
    æł©æł©
    0.08
    λή
    0.08
     ÐłÐ°ÑģÑģка
    0.08
    ä¸Ģå¸Ĩ
    0.08
    éton
    0.08
    olik
    0.08
    Activations Density 0.023%

    No Known Activations