© 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. 20437
    Prev
    Next
    INDEX
    Explanations

    something like

    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
    er
    -0.11
    ments
    -0.10
    ities
    -0.09
    argest
    -0.09
    ermen
    -0.09
    ÙĬÙĩ
    -0.09
    æŁIJä¸Ģ
    -0.09
    eru
    -0.08
    ëĭ¤ê³ł
    -0.08
    erais
    -0.08
    POSITIVE LOGITS
     else
    0.11
     like
    0.08
     akin
    0.08
     anderem
    0.08
    akin
    0.08
     anderes
    0.07
    place
    0.07
    åı«åģļ
    0.07
    fois
    0.07
    же
    0.07
    Activations Density 0.057%

    No Known Activations