© 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. 29175
    Prev
    Next
    INDEX
    Explanations

    section titles or keywords

    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
    orca
    -0.07
    æł¸
    -0.07
    èļ¤
    -0.07
    æļĩ
    -0.07
    ิà¹Īà¸ĩ
    -0.07
    सन
    -0.06
    kit
    -0.06
    usul
    -0.06
    ES
    -0.06
    Ùģس
    -0.06
    POSITIVE LOGITS
    inox
    0.07
    ommel
    0.07
    SocketAddress
    0.07
    çĻ½éĩij
    0.07
    åıĪå°Ĩ
    0.07
    åı¦ä¸Ģ端
    0.06
    ainers
    0.06
    çŃł
    0.06
    人马
    0.06
    emaker
    0.06
    Activations Density 0.328%

    No Known Activations