© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42531
    Prev
    Next
    INDEX
    Explanations

    list or array

    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
    个åĽŀçŃĶ
    -0.08
     éve
    -0.08
    æľ¬çıŃ
    -0.08
    isd
    -0.07
    ãĤ»ãĥ©
    -0.07
    etid
    -0.07
    缸åħ³èµĦæĸĻ
    -0.07
    orsch
    -0.07
    kund
    -0.07
    resizing
    -0.07
    POSITIVE LOGITS
    T
    0.07
    éĩįåıł
    0.07
    ä¹ĭåIJİçļĦ
    0.06
    Âł
    0.06
    ega
    0.06
     sai
    0.06
     am
    0.06
    ial
    0.06
     mal
    0.06
    å°±æĺ¯ä¸Ģç§į
    0.06
    Activations Density 0.589%

    No Known Activations