© 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. 34226
    Prev
    Next
    INDEX
    Explanations

    proportional, approximately, equal

    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
    iland
    -0.09
    zak
    -0.09
    mutable
    -0.09
    undry
    -0.08
    -hooks
    -0.08
    áĢ±áĢ¬áĢº
    -0.08
    òi
    -0.08
    acca
    -0.08
    âĨIJ
    -0.07
    æĺĬ天
    -0.07
    POSITIVE LOGITS
     proportional
    0.11
     roughly
    0.10
    ä¼°ç®Ĺ
    0.10
     equal
    0.09
     approximately
    0.09
     doubling
    0.09
    大约
    0.09
    æµĭç®Ĺ
    0.09
    ç²Ĺçķ¥
    0.09
     calculate
    0.09
    Activations Density 0.078%

    No Known Activations