© 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. 32676
    Prev
    Next
    INDEX
    Explanations

    consistent with

    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
    ¾
    -0.09
    اÙħر
    -0.08
    ueb
    -0.07
    коÑĤ
    -0.07
     Mots
    -0.07
    æĸ°åĬŁèĥ½
    -0.07
    algo
    -0.07
    ·¸
    -0.07
    ãĤ¿ãĥ«
    -0.06
    Ä«g
    -0.06
    POSITIVE LOGITS
    à¸ģัà¸ļà¸ģาร
    0.08
    apa
    0.08
     both
    0.07
    à¸ģารà¸ĵà¹Į
    0.07
    borg
    0.07
    umpah
    0.07
    ãģ¥
    0.07
    emand
    0.07
     faptul
    0.07
    äºİä¸Ģ
    0.07
    Activations Density 0.014%

    No Known Activations