© 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. 24493
    Prev
    Next
    INDEX
    Explanations

    field of the invention

    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
    imgs
    -0.07
    ntag
    -0.07
    åĴĮä¸į
    -0.07
     Outputs
    -0.07
    ocab
    -0.07
    åīįæıIJ
    -0.07
    æĢİä¹Īåİ»
    -0.07
    íķŃ
    -0.07
     &
    -0.07
    èĸĩ
    -0.07
    POSITIVE LOGITS
    cratch
    0.07
    éĢ»
    0.07
    azu
    0.07
    åĪĨ为
    0.07
     consists
    0.07
    åıŃ
    0.06
    åĺ¶
    0.06
    èĶ¼
    0.06
     consisted
    0.06
    ä¹ı
    0.06
    Activations Density 0.003%

    No Known Activations