© 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. 33016
    Prev
    Next
    INDEX
    Explanations

    parent element or property

    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
    umente
    -0.10
    plorer
    -0.08
    iland
    -0.08
    tritts
    -0.08
    aknya
    -0.07
    olated
    -0.07
    หมาย
    -0.07
     pháºŃn
    -0.07
    ecast
    -0.07
     ÙĪاÙĦØ«ÙĤ
    -0.07
    POSITIVE LOGITS
    less
    0.10
    è¾Ī
    0.10
    esco
    0.09
    ship
    0.09
    hood
    0.09
    aceous
    0.09
    -child
    0.09
    chaft
    0.09
    esis
    0.08
    azgo
    0.08
    Activations Density 0.032%

    No Known Activations