© 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. 32146
    Prev
    Next
    INDEX
    Explanations

    two lists or arrays

    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
    rap
    -0.09
    ÑĢк
    -0.08
    ä¸ĢæĭĽ
    -0.08
    reon
    -0.08
    ä¸Ģç«Ļ
    -0.08
    åİŁåĪĽä½ľåĵģ
    -0.07
     pii
    -0.07
    asih
    -0.07
    fraction
    -0.07
    éĩ
    -0.07
    POSITIVE LOGITS
     copy
    0.08
    ICLE
    0.08
    å¤ĩ
    0.07
     contain
    0.07
    তà§ĩ
    0.07
    å¾ħ
    0.07
    agram
    0.07
    æIJľç´¢
    0.07
     compar
    0.07
    ä¸ŃçļĦæīĢæľī
    0.07
    Activations Density 0.062%

    No Known Activations