© 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. 8637
    Prev
    Next
    INDEX
    Explanations

    defined as

    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
    以åħįå½±åĵį
    -0.08
    ajos
    -0.08
    管çIJĨ模å¼ı
    -0.08
    ynn
    -0.07
    noinspection
    -0.07
    åıªæĥ³
    -0.07
     affect
    -0.07
    åĨį继ç»Ń
    -0.07
    mous
    -0.07
    éĥ½æĺ¯æ¯Ķè¾ĥ
    -0.07
    POSITIVE LOGITS
     definition
    0.10
    å®ļä¹ī为
    0.09
    definition
    0.09
    æµĭéĩı
    0.08
    æĪĸçĶ±
    0.08
    å®ļä¹ī
    0.08
     definitions
    0.08
    Definition
    0.08
     Definition
    0.08
    å®ļä¹īçļĦ
    0.07
    Activations Density 0.017%

    No Known Activations