© 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. 32365
    Prev
    Next
    INDEX
    Explanations

    articles followed by specific nouns

    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
    able
    -0.07
    arian
    -0.07
    arani
    -0.07
    æĥķ
    -0.06
    åĬłæĭ¿å¤§
    -0.06
    aus
    -0.06
    æŀī
    -0.06
    ed
    -0.06
    ::<
    -0.06
    boxed
    -0.06
    POSITIVE LOGITS
    üp
    0.08
    ologically
    0.08
    ullets
    0.08
    ologies
    0.08
     инÑĭм
    0.08
     Personali
    0.08
    à¹Ģà¸Ķีย
    0.07
    aters
    0.07
     originals
    0.07
     olds
    0.07
    Activations Density 1.107%

    No Known Activations