© 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. 21838
    Prev
    Next
    INDEX
    Explanations

    stabilizing by making stable

    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
    蹬
    -0.07
    chal
    -0.07
     Fortunately
    -0.07
    اÙħÙĬØ©
    -0.07
    udan
    -0.06
    宫
    -0.06
    stairs
    -0.06
    ud
    -0.06
    å¿ĥ声
    -0.06
    umph
    -0.06
    POSITIVE LOGITS
    驹
    0.08
     diri
    0.08
    /support
    0.07
    icher
    0.07
    ipc
    0.07
    amal
    0.07
    ÑĢÑĥк
    0.07
    ãĥ³ãĥĪ
    0.07
    ç¨ĭ度ä¸Ĭ
    0.07
    åIJİæİĴ
    0.07
    Activations Density 0.005%

    No Known Activations