© 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. 57474
    Prev
    Next
    INDEX
    Explanations

    other or adjacent

    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
    对æľī
    -0.09
    ANIA
    -0.08
    ç§ĭæľĪ
    -0.08
    CTYPE
    -0.08
    è²Ķ
    -0.08
    è§ij
    -0.08
    ETE
    -0.08
    gai
    -0.07
     tats
    -0.07
    .creator
    -0.07
    POSITIVE LOGITS
     nearby
    0.09
    åIJĮä¼´
    0.08
     neighboring
    0.08
     adjacent
    0.08
     another
    0.08
     counterparts
    0.08
     اÙĦآخرÙĬÙĨ
    0.07
    åĴĮèĩªå·±
    0.07
     дÑĢÑĥгое
    0.07
    åĪ°åħ¶ä»ĸ
    0.07
    Activations Density 0.092%

    No Known Activations