© 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. 11009
    Prev
    Next
    INDEX
    Explanations

    based on

    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
    Ñħов
    -0.08
    ylv
    -0.08
    çĥŃå¿ĥ
    -0.08
    assis
    -0.08
    åªĴ
    -0.07
    rott
    -0.07
    aras
    -0.07
     Pickup
    -0.07
    ilien
    -0.07
    ATER
    -0.07
    POSITIVE LOGITS
    opy
    0.08
    è¯Ńæ°Ķ
    0.07
    åĬ¨è¯į
    0.07
    æĢģåĬ¿
    0.07
    ender
    0.07
     verbs
    0.07
    pare
    0.07
    á»ijt
    0.07
    orse
    0.07
    çİĭçīĮ
    0.07
    Activations Density 0.083%

    No Known Activations