© 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. 51546
    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
    Ĥ
    -0.07
    hado
    -0.07
    iland
    -0.07
    éļ¶å±ŀ
    -0.07
    vers
    -0.07
    conti
    -0.07
    utul
    -0.07
    项
    -0.06
    istro
    -0.06
    rava
    -0.06
    POSITIVE LOGITS
     Elim
    0.07
    累累
    0.07
    ocio
    0.07
    chw
    0.07
     Ganz
    0.07
    elim
    0.07
    使çĶ¨æŶéĹ´
    0.07
    æľĢåıĹ
    0.06
    æĩĴ
    0.06
    ä¸įèĢĥèĻij
    0.06
    Activations Density 0.000%

    No Known Activations