© 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. 3342
    Prev
    Next
    INDEX
    Explanations

    step number

    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
    iesel
    -0.08
    ArrayType
    -0.08
    ehme
    -0.07
    ãĥıãĥ©
    -0.07
    类似çļĦ
    -0.07
    æľīå°ı
    -0.07
    æĺ¯ä¸Ģ大
    -0.07
    .DependencyInjection
    -0.07
    é¢ĦåĮħè£ħ
    -0.07
    缸çľĭ
    -0.06
    POSITIVE LOGITS
     step
    0.08
    第ä¸īæŃ¥
    0.08
     Step
    0.07
    æŃ¥éª¤
    0.07
    Step
    0.07
     ÑĪаг
    0.07
    -step
    0.07
    ç¬¬åĽĽæŃ¥
    0.07
    auj
    0.07
    第äºĮæŃ¥
    0.07
    Activations Density 0.002%

    No Known Activations