© 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. 46378
    Prev
    Next
    INDEX
    Explanations

    numbers and quantities

    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
    åľ¨çĶ¨
    -0.07
    /providers
    -0.07
     zdec
    -0.07
    è®¾åľ¨
    -0.07
    æű
    -0.07
    æ·±å¾Ĺ
    -0.07
    åľ³
    -0.07
     Accord
    -0.07
    å²±
    -0.06
    ä¸īèī²
    -0.06
    POSITIVE LOGITS
    ivia
    0.09
    ä¿Ŀè¯ģåħ¶
    0.08
    为åħ¶
    0.07
    acha
    0.07
    aze
    0.07
    èĶĵ
    0.07
    ftime
    0.07
    פ×ķת
    0.07
    enga
    0.07
    à¹Ģ
    0.06
    Activations Density 0.016%

    No Known Activations