© 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. 30869
    Prev
    Next
    INDEX
    Explanations

    soul's beauty, tattooed hunter, artery treatments, liquid handling, malonic esters

    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
    ÃīM
    -0.07
    çº¢æŁ¿
    -0.07
    endon
    -0.07
    ζί
    -0.07
    羣æŃ£æĦıä¹īä¸ĬçļĦ
    -0.07
    zien
    -0.07
    aktion
    -0.07
    ypi
    -0.07
    羣æŃ£å®ŀçİ°
    -0.07
    ajs
    -0.06
    POSITIVE LOGITS
    -related
    0.08
    -oriented
    0.07
    erness
    0.07
    è¡Įä¹ĭ
    0.07
     honoured
    0.07
    æŶä¸ĭ
    0.07
    ev
    0.06
    åĢ
    0.06
    ç§ī
    0.06
    sung
    0.06
    Activations Density 0.482%

    No Known Activations