© 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. 43075
    Prev
    Next
    INDEX
    Explanations

    receive a / euros

    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
    人æ°ijåħ±åĴĮåĽ½
    -0.10
    quina
    -0.08
    tering
    -0.07
    laise
    -0.07
    åIJĪçIJĨ使çĶ¨
    -0.07
    terior
    -0.07
    wijk
    -0.07
    æ°Ĺãģ«
    -0.07
     Sadd
    -0.07
    möglich
    -0.07
    POSITIVE LOGITS
    åĪ°çļĦ
    0.10
    /send
    0.10
    ieves
    0.09
    OrCreate
    0.08
    ables
    0.08
    ivities
    0.08
    รà¸Ńà¸ĩ
    0.08
    ivity
    0.08
    ives
    0.07
    åĴĮå¤ĦçIJĨ
    0.07
    Activations Density 0.069%

    No Known Activations