© 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. 40182
    Prev
    Next
    INDEX
    Explanations

    options or devices

    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
    è¦ģä¹Īæĺ¯
    -0.08
    è¦ģä¹Ī
    -0.07
    -author
    -0.07
    çĽĸä¸ĸ
    -0.06
    ên
    -0.06
     Rape
    -0.06
     Oaks
    -0.06
    豫
    -0.06
    ÙĪØ·
    -0.06
    anter
    -0.06
    POSITIVE LOGITS
     downright
    0.10
    æ··åIJĪåŀĭ
    0.10
    å¤įåIJĪåŀĭ
    0.09
    à¸Ńืà¹Īà¸Ļà¹Ĩ
    0.09
     miscellaneous
    0.08
    以ä¸Ĭ
    0.08
    è§Ħå®ļçļĦåħ¶ä»ĸ
    0.08
     infine
    0.08
     ìĭ¬ì§Ģìĸ´
    0.08
     ÑģобÑģÑĤвенно
    0.08
    Activations Density 0.272%

    No Known Activations