© 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. 13219
    Prev
    Next
    INDEX
    Explanations

    list items and descriptions

    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
    imea
    -0.07
     Raleigh
    -0.07
     plutôt
    -0.07
    antt
    -0.07
    uze
    -0.07
    ÏĦήÏģιο
    -0.07
    вне
    -0.07
    imia
    -0.07
    иÑĤоÑĢ
    -0.07
    è¯ģå®ŀåħ¶
    -0.07
    POSITIVE LOGITS
    iebe
    0.07
    æĤ²æ¬¢
    0.07
    arend
    0.07
     Pare
    0.07
    DO
    0.07
    antics
    0.07
    æĹłè¯Ń
    0.07
    nder
    0.07
     caus
    0.06
     portray
    0.06
    Activations Density 0.003%

    No Known Activations