© 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. 61440
    Prev
    Next
    INDEX
    Explanations

    titles starting with "a" or "the"

    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
    اØŃ
    -0.08
    ous
    -0.07
    оÑģÑģ
    -0.07
    éĺ¿éĩĮ
    -0.06
    omm
    -0.06
    æ¼ı
    -0.06
    hte
    -0.06
     degrad
    -0.06
    #####
    -0.06
    笼
    -0.06
    POSITIVE LOGITS
    rance
    0.08
    elves
    0.08
    /share
    0.08
    èIJ¦
    0.08
    åģļ大
    0.08
    atown
    0.08
    média
    0.08
    èģĶ系客æľį
    0.07
    aston
    0.07
    oire
    0.07
    Activations Density 0.002%

    No Known Activations