© 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. 26546
    Prev
    Next
    INDEX
    Explanations

    love between the covers

    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
    angler
    -0.08
    oyer
    -0.07
    àºĦ
    -0.07
    ç»Ŀåľ°
    -0.07
    åħ¹
    -0.07
    جÙĨ
    -0.07
     Bot
    -0.07
    atnya
    -0.07
    ardi
    -0.07
    åĮºåĨħ
    -0.07
    POSITIVE LOGITS
    poons
    0.08
    èĩªå·±çļĦèĥ½åĬĽ
    0.07
    imb
    0.07
    羣çIJĨ
    0.07
    èĥ½åĬĽ
    0.07
    Å¡ky
    0.07
    اغ
    0.06
    ÙĪراÙĨ
    0.06
    +xml
    0.06
    елей
    0.06
    Activations Density 0.009%

    No Known Activations