© 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. 34260
    Prev
    Next
    INDEX
    Explanations

    performances, plays, residential, embark, exchanges, bicycle

    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
    forge
    -0.07
     combin
    -0.06
    alling
    -0.06
    微信群
    -0.06
    贯穿äºİ
    -0.06
     unl
    -0.06
    éģ¥è¿ľçļĦ
    -0.06
    çĶ¨å¾®ä¿¡
    -0.06
    çĶ¨åľ¨
    -0.06
    çĶŁäºİ
    -0.06
    POSITIVE LOGITS
    åľ¨éĩĮéĿ¢
    0.16
     allÃŃ
    0.15
    åľ¨éĤ£éĩĮ
    0.15
    åľ¨åħ¶ä¸Ń
    0.14
    å°±åľ¨è¿ĻéĩĮ
    0.13
    éĥ½åľ¨è¿ĻéĩĮ
    0.13
     dort
    0.12
    åľ¨ä¸ĬéĿ¢
    0.12
     therein
    0.12
     ÑĤÑĥда
    0.12
    Activations Density 0.749%

    No Known Activations