© 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. 38794
    Prev
    Next
    INDEX
    Explanations

    #include <stdio.h>

    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
    çļĦ
    -0.13
    ÛĮ
    -0.12
    缸è¾ħ缸æĪIJ
    -0.12
    ä¸įåı¯æĢĿè®®
    -0.11
    nya
    -0.11
    áĥ¡
    -0.10
    äºĭåįĬåĬŁåĢį
    -0.10
    çļĦèµ°åĬ¿
    -0.10
    æĸ°åĬłåĿ¡
    -0.10
    身临åħ¶å¢ĥ
    -0.09
    POSITIVE LOGITS
    Ø©
    0.15
    ãĥ³ãĤ°
    0.09
    ity
    0.09
    ën
    0.09
    اÙģتÙĩ
    0.08
    ìĸ´ë²Ħ
    0.08
    (sh
    0.08
    reiber
    0.08
    icken
    0.08
    Ò£
    0.08
    Activations Density 0.005%

    No Known Activations