© 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. 29604
    Prev
    Next
    INDEX
    Explanations

    brute force

    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
    为主ä½ĵ
    -0.07
    主ä½ĵ
    -0.07
    opher
    -0.06
    onale
    -0.06
    为主ä½ĵçļĦ
    -0.06
     Lah
    -0.06
    ä¸ŃçļĦä¸Ģ
    -0.06
    亲身ç»ıåİĨ
    -0.06
    .VERSION
    -0.06
    èĮĹ
    -0.06
    POSITIVE LOGITS
    urado
    0.09
    èĴĻ
    0.08
    ertools
    0.08
    urada
    0.08
    estino
    0.07
    iés
    0.07
    ljan
    0.07
    ilde
    0.07
     computational
    0.07
    رÙĪت
    0.07
    Activations Density 0.002%

    No Known Activations