© 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. 65042
    Prev
    Next
    INDEX
    Explanations

    numbers with formatting

    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
    èī¯
    -0.08
    æķ¬
    -0.07
    enville
    -0.07
    ashian
    -0.07
    xDF
    -0.07
    弯
    -0.07
    ãģĨãģ¡ãģ«
    -0.07
    entic
    -0.07
    弯弯
    -0.07
    rlen
    -0.07
    POSITIVE LOGITS
    åĨ
    0.07
    å¡ļ
    0.07
    à¸Ħร
    0.06
    æĬĬ人
    0.06
    ãģ»
    0.06
    以身
    0.06
     dán
    0.06
    plex
    0.06
    pia
    0.06
    upu
    0.06
    Activations Density 0.061%

    No Known Activations