© 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. 32347
    Prev
    Next
    INDEX
    Explanations

    numbers with commas and decimals

    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
    ambu
    -0.08
    echa
    -0.07
    hrad
    -0.07
    롬
    -0.07
    ä½Ĩåĩ¡
    -0.07
    паÑĢÑĤа
    -0.07
    tec
    -0.07
    çİĩä½İ
    -0.06
    Ec
    -0.06
    icho
    -0.06
    POSITIVE LOGITS
    ä¼¼æĺ¯
    0.08
    £
    0.07
    ä¼¼
    0.07
    貫
    0.07
    ressive
    0.07
    çļĦè¿ij
    0.07
    åĩłåĪĨ
    0.07
     something
    0.07
    finger
    0.07
    åĬłè½½ä¸Ń
    0.07
    Activations Density 0.015%

    No Known Activations