© 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. 57503
    Prev
    Next
    INDEX
    Explanations

    Comments, Link, By, We

    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
    ÑĢев
    -0.07
    OLON
    -0.07
    ael
    -0.07
    uli
    -0.06
    ürt
    -0.06
    nard
    -0.06
    edi
    -0.06
    åľ¨éĩĮéĿ¢
    -0.06
     reto
    -0.06
    å¾Īæ¸ħæ¥ļ
    -0.06
    POSITIVE LOGITS
    äk
    0.07
    为人æ°ij
    0.07
    ÑĦÑĤа
    0.07
    æ´ĭ
    0.07
     tamp
    0.07
    ovah
    0.07
    assis
    0.07
    asses
    0.07
    zung
    0.07
    Began
    0.07
    Activations Density 0.004%

    No Known Activations