© 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. 40220
    Prev
    Next
    INDEX
    Explanations

    direct connection

    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
    åħ¢åħ¢
    -0.08
    ä¸įæĦģ
    -0.08
    rena
    -0.07
    orrent
    -0.07
    lah
    -0.06
    ä¸įèĥ½å®Įåħ¨
    -0.06
    кладки
    -0.06
    ällen
    -0.06
    THR
    -0.06
    ÑĤÑĢ
    -0.06
    POSITIVE LOGITS
     directly
    0.24
    缴æİ¥
    0.23
     direct
    0.23
    缴æİ¥ä»İ
    0.22
    缴æİ¥è¿Ľåħ¥
    0.21
    缴æİ¥ä¸İ
    0.21
     directo
    0.21
    缴æİ¥åIJij
    0.21
    direct
    0.21
    缴æİ¥çļĦ
    0.21
    Activations Density 0.111%

    No Known Activations