© 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. 58569
    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
     Podesta
    -0.07
    zik
    -0.07
    æµģ
    -0.07
    æµģç»ı
    -0.06
    æĸ°åĨłèĤºçĤİçĸ«æĥħ
    -0.06
    ropa
    -0.06
    çĤ¹å¤ļ
    -0.06
    _mgr
    -0.06
    ubby
    -0.06
    åĪĺæĻĵ
    -0.06
    POSITIVE LOGITS
     tonel
    0.08
    èĹIJ
    0.08
    æĪijåIJ§
    0.07
    éĭŃ
    0.07
    åĿĤ
    0.07
     ton
    0.07
    رتÙĪÙĨ
    0.07
    Finite
    0.07
    hada
    0.06
    alang
    0.06
    Activations Density 0.000%

    No Known Activations