© 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. 10952
    Prev
    Next
    INDEX
    Explanations

    how about: or perhaps

    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
    ĮĢ
    -0.10
    [âĢ¦
    -0.09
    ACES
    -0.09
    åĵªäºĽæĸ¹éĿ¢
    -0.08
    æľīåĵª
    -0.08
    (...)
    -0.08
     (...)
    -0.08
     (...
    -0.08
    ')['
    -0.07
    UTURE
    -0.07
    POSITIVE LOGITS
    ãĥ»ãĥ»ãĥ»ãĥ»ãĥ»ãĥ»ãĥ»ãĥ»
    0.07
    åħĪæĬĬ
    0.07
    åºĶ该æĺ¯
    0.06
    å¦Ĥæŀľæĺ¯
    0.06
    Mark
    0.06
    alan
    0.06
    fern
    0.06
    åĿ¤
    0.06
    ennie
    0.06
    åį¡å°Ķ
    0.06
    Activations Density 2.426%

    No Known Activations