© 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. 18134
    Prev
    Next
    INDEX
    Explanations

    order divides, global dimension, path length

    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
    ERRU
    -0.08
    á»ĩt
    -0.07
    reur
    -0.07
    æķ¸éĩı
    -0.07
    asje
    -0.07
    ç§ģèĩª
    -0.07
    .Standard
    -0.07
     Vern
    -0.07
    ney
    -0.07
    ä¸Ģ家ä¸īåı£
    -0.07
    POSITIVE LOGITS
    è¾ĥçŁŃ
    0.08
    é£İè½»
    0.08
     max
    0.07
     getMax
    0.07
    à¸Ĭำระ
    0.06
    itus
    0.06
    weite
    0.06
     Shepard
    0.06
    (max
    0.06
    çĶ³æĺİ
    0.06
    Activations Density 0.001%

    No Known Activations