© 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. 47792
    Prev
    Next
    INDEX
    Explanations

    numbers and lists

    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
    erin
    -0.07
    åºĶæľīå°½æľī
    -0.07
    RAFT
    -0.07
     Boeh
    -0.07
    неÑĢ
    -0.07
    lehr
    -0.07
    ì§Ģ기
    -0.07
    izzer
    -0.07
    æŀī
    -0.07
    è¿ĺæľīå¾Īå¤ļ
    -0.06
    POSITIVE LOGITS
    çĶ¸
    0.08
    ãĢħ
    0.08
    째
    0.08
    ï¸İ
    0.07
    æ¡£
    0.07
    ä¹ĭ交
    0.07
    ibern
    0.07
    ái
    0.07
    oli
    0.07
    åĬłç´¢
    0.06
    Activations Density 0.017%

    No Known Activations