© 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. 3627
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    é¦ģ
    -0.08
    åľ¨åŃ¦ä¹łä¸Ĭ
    -0.08
    ạc
    -0.08
    俨
    -0.08
    onge
    -0.07
    enson
    -0.07
    vaj
    -0.07
    ãĥĨãĥł
    -0.07
    æĺıæĺı
    -0.07
    ukup
    -0.07
    POSITIVE LOGITS
    abo
    0.08
    R
    0.06
    ike
    0.06
    æ¤į
    0.06
    'T
    0.06
    ç§ĭåĨ¬
    0.06
    anch
    0.06
    åħŃçĽĺ
    0.06
     R
    0.06
    '
    0.06
    Activations Density 0.000%

    No Known Activations