© 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. 61690
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with numbers

    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
    æ°¸çĶŁ
    -0.07
    umba
    -0.07
    容
    -0.07
     Gros
    -0.07
     ano
    -0.07
    æĸ¯é¡¿
    -0.07
    ellig
    -0.07
    anus
    -0.06
    tol
    -0.06
    pch
    -0.06
    POSITIVE LOGITS
    æĺ¯æľĢ大çļĦ
    0.09
    æıŃ
    0.07
    ä½Ĩæĺ¯åĽłä¸º
    0.07
    åį´åĽłä¸º
    0.07
     ActionTypes
    0.07
    HTTPRequest
    0.07
    æĺ¯æľĢ
    0.07
    çĶ°å¸Ĥ
    0.07
     Armour
    0.06
    HS
    0.06
    Activations Density 0.032%

    No Known Activations