© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 19190
    Prev
    Next
    INDEX
    Explanations

    JSON structure elements

    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
    åĩ«
    -0.08
    \\\\
    -0.08
    éͦæłĩ
    -0.07
    icina
    -0.07
    arz
    -0.07
    panic
    -0.07
    ãģ¾ãģĹãģ¦
    -0.07
    бÑĢе
    -0.07
    raf
    -0.07
    à®Łà¯Ī
    -0.07
    POSITIVE LOGITS
    èͬ
    0.07
    ï¼Į“
    0.07
    ).__
    0.06
    иви
    0.06
    ishly
    0.06
    ï¼ĮãĢĬ
    0.06
    éĩĮäºļ
    0.06
    çļĦéĤ£ç§į
    0.06
    pios
    0.06
    istros
    0.06
    Activations Density 0.081%

    No Known Activations