© 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. 39429
    Prev
    Next
    INDEX
    Explanations

    craft beer brewery

    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
    ãĤĪãģĨãģª
    -0.08
    hood
    -0.07
    о
    -0.07
    istrator
    -0.07
    gether
    -0.07
    coln
    -0.07
    earch
    -0.07
    nable
    -0.07
    cape
    -0.07
    iated
    -0.06
    POSITIVE LOGITS
    åĬłæĭ¿å¤§
    0.09
    riott
    0.08
    kana
    0.08
    urally
    0.08
     пÑĢоезда
    0.08
    abra
    0.08
    ierto
    0.08
    gerecht
    0.08
    sweise
    0.08
    uture
    0.07
    Activations Density 0.085%

    No Known Activations