© 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. 62333
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and code

    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
    utang
    -0.07
    ambang
    -0.07
    ellet
    -0.07
    agl
    -0.07
    æīİå®ŀåģļ好
    -0.06
    ahui
    -0.06
    æĸĭ
    -0.06
     beet
    -0.06
    æłĭ
    -0.06
    -0.06
    POSITIVE LOGITS
    grafer
    0.09
    typeid
    0.08
    terer
    0.08
    еÑĢбÑĥ
    0.08
    lessness
    0.08
    àºĩ
    0.08
    è¡ĢçĹĩ
    0.07
    æķ´ä¸ªéĹ®é¢ĺ
    0.07
    ç§ijæĸ¯
    0.07
    置身äºİ
    0.07
    Activations Density 0.007%

    No Known Activations