© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 26952
    Prev
    Next
    INDEX
    Explanations

    motivic mathematics, mirror symmetry, representations

    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
    ewire
    -0.07
    å¸Ĥ人æ°ijæ³ķéĻ¢
    -0.07
    -0.07
    TeX
    -0.07
     DIN
    -0.06
    apat
    -0.06
     Pare
    -0.06
    metics
    -0.06
    沫
    -0.06
    èģĶç³»åľ°åĿĢ
    -0.06
    POSITIVE LOGITS
    å±±å·Ŀ
    0.08
     estimates
    0.08
     Echo
    0.08
    æ¼Ĩ
    0.08
     Passport
    0.08
     Estimates
    0.08
     passports
    0.07
    éķ¿çĽ¸
    0.07
    upload
    0.07
    rias
    0.07
    Activations Density 0.015%

    No Known Activations