© 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. 29564
    Prev
    Next
    INDEX
    Explanations

    `products`, `infections`, `viruse`

    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
    è¿Ń
    -0.08
    -equipped
    -0.08
     tol
    -0.08
    Ñĩок
    -0.07
    åĴĮé£İéĻ©
    -0.07
    aman
    -0.07
    ç¥ĸåĽ½
    -0.07
    人们çļĦçĶŁæ´»
    -0.07
    aglio
    -0.07
    åĬ²åĦ¿
    -0.07
    POSITIVE LOGITS
    -specific
    0.11
    -wide
    0.10
    èĩªå¸¦çļĦ
    0.09
    æľ¬èº«çļĦ
    0.08
    -level
    0.08
    éĻħ
    0.08
    pecific
    0.08
    -side
    0.08
    åĨħçļĦ
    0.08
    -facing
    0.08
    Activations Density 0.708%

    No Known Activations