© 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. 61149
    Prev
    Next
    INDEX
    Explanations

    field names or types

    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
    ÙĦز
    -0.07
    ibo
    -0.07
    ÑģÑĤÑĢе
    -0.07
    nai
    -0.07
    .Criteria
    -0.07
     Bake
    -0.07
    bler
    -0.07
    设计è¦ģæ±Ĥ
    -0.07
    ocz
    -0.07
     >&
    -0.07
    POSITIVE LOGITS
    ç¬Ķä¸ĭçļĦ
    0.07
    (*)(
    0.07
    çļĦä¸Ģ大
    0.06
    ialized
    0.06
    è´¨
    0.06
    armo
    0.06
    çħĻ
    0.06
    AYA
    0.06
    -oper
    0.06
     ral
    0.06
    Activations Density 0.010%

    No Known Activations