© 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. 31826
    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
    اÙĨÙĩ
    -0.07
    ITAS
    -0.06
    kiye
    -0.06
    allah
    -0.06
    éĻĢèŀº
    -0.06
    æ¡ij
    -0.06
    纵çĦ¶
    -0.06
    èĽŁé¾Ļ
    -0.06
    åħ«ä¸ª
    -0.06
    áĥļáĥĺ
    -0.06
    POSITIVE LOGITS
    زش
    0.09
    .sul
    0.08
    èģĶåĤ¨
    0.07
    ¶ļ
    0.07
    å»·
    0.07
    £¼
    0.07
    odes
    0.07
    rypt
    0.07
    èĩ³åħ³
    0.07
    istica
    0.07
    Activations Density 0.000%

    No Known Activations