© 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. 46398
    Prev
    Next
    INDEX
    Explanations

    files, hospitals, dating, extractions

    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
     inilah
    -0.09
    ardy
    -0.08
    .dylib
    -0.08
    atteri
    -0.08
    çªľ
    -0.08
    arpa
    -0.08
    éģĹ失
    -0.08
     loss
    -0.07
    යà·Ĵ
    -0.07
    loss
    -0.07
    POSITIVE LOGITS
    åĬ¡
    0.07
    ç±»æݨ
    0.06
    ium
    0.06
    ocere
    0.06
    éĥijéĩį声æĺİ
    0.06
    pecific
    0.06
    Generic
    0.06
     specifically
    0.06
    æĤī
    0.06
    åIJĦ级åIJĦç±»
    0.06
    Activations Density 0.029%

    No Known Activations