© 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. 56747
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    çĽ¸å¯¹
    -0.08
     arguably
    -0.08
     relatively
    -0.07
     reasonably
    -0.07
     relative
    -0.07
    åħ¸åŀĭ
    -0.07
     devoted
    -0.07
    relative
    -0.07
    è¾ĥ
    -0.06
    “
    -0.06
    POSITIVE LOGITS
    yles
    0.09
    表示èĩªå·±
    0.08
    çľ¼çĿģ
    0.08
    åŃĺåĤ¨åľ¨
    0.08
    äºij彩
    0.08
    æĹłå½±
    0.08
    (___
    0.08
    大æĥĬ
    0.08
    çŁ¥éģĵä»ĸ
    0.08
    latlong
    0.08
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.