© 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. 64185
    Prev
    Next
    INDEX
    Explanations

    ( and | ) operators

    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
    heimer
    -0.07
    究åħ¶åİŁåĽł
    -0.07
    ä¸Ń大
    -0.06
    åħī大
    -0.06
     discre
    -0.06
    ondi
    -0.06
    .ping
    -0.06
    кÑĥлÑıÑĢ
    -0.06
    æŀľåŃIJ
    -0.06
    æł¹æľ¬ä¸į
    -0.06
    POSITIVE LOGITS
    phant
    0.07
    LETTE
    0.07
    ESA
    0.07
    IFT
    0.07
     ÑģобÑĸ
    0.07
    åįģä½³
    0.06
    kke
    0.06
    akening
    0.06
    רת
    0.06
    åį³å¢¨
    0.06
    Activations Density 0.021%

    No Known Activations