© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16185
    Prev
    Next
    INDEX
    Explanations

    forecast period

    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
    建设ä¸İ
    -0.07
    ×Ĺ׳×ķ
    -0.07
    ÑĢож
    -0.07
     Schles
    -0.07
    ifr
    -0.07
    åĨħéĥ¨çļĦ
    -0.06
    åľ¨è¿Ļåľº
    -0.06
    èĢħ为
    -0.06
    ajer
    -0.06
    inu
    -0.06
    POSITIVE LOGITS
    åľ°çĤ¹
    0.10
     locations
    0.10
    æŶéĹ´æ®µ
    0.10
     меÑģÑĤа
    0.10
    åĮºåŁŁ
    0.10
     area
    0.10
    åĮºéĹ´
    0.09
    à¸ŀืà¹īà¸Ļà¸Ĺีà¹Ī
    0.09
     endroit
    0.09
     miejsca
    0.09
    Activations Density 0.453%

    No Known Activations