© 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. 49375
    Prev
    Next
    INDEX
    Explanations

    group order

    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
    ä¸ĢæĿŁ
    -0.07
    ichtung
    -0.07
    èĦijæµ·
    -0.07
     deliveries
    -0.07
    andler
    -0.07
    puter
    -0.06
    ç»Ĵæ¯Ľ
    -0.06
    ilat
    -0.06
     receivers
    -0.06
    é«ĺ级ä¸ŃåѦ
    -0.06
    POSITIVE LOGITS
    eson
    0.09
    apsed
    0.08
    æľĢçŁŃ
    0.08
    =length
    0.07
    gon
    0.07
    æľĢéķ¿çļĦ
    0.07
    -length
    0.07
    utom
    0.07
    -duration
    0.07
    éķ¿çŁŃ
    0.07
    Activations Density 0.002%

    No Known Activations