© 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. 64360
    Prev
    Next
    INDEX
    Explanations

    social behaviors and media

    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
    éĥ¨ä»½
    -0.09
    éĨ
    -0.08
    esak
    -0.08
    èĮĥæĸĩç½ij
    -0.07
    å¾ĢéĩĮ
    -0.07
    åIJĦå¤Ħ
    -0.07
    éģĵéģĵ
    -0.07
    aney
    -0.07
    éĥ¨åĪĨ
    -0.07
    Queries
    -0.06
    POSITIVE LOGITS
    æĺ¯ä¸Ģç§į常è§ģçļĦ
    0.07
    æľ¬çłĶ究
    0.07
     versus
    0.07
    äºĨä¸Ģ款
    0.07
     embodied
    0.07
     typ
    0.07
     ****************************************************************************
    0.07
    ervis
    0.07
    ufs
    0.07
    æĺ¯ä¸Ģ款
    0.07
    Activations Density 1.297%

    No Known Activations