© 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. 50377
    Prev
    Next
    INDEX
    Explanations

    group records

    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
    ufer
    -0.11
    estig
    -0.10
    ernt
    -0.10
    angkok
    -0.10
    ê°Ģ족
    -0.09
    ëĮĢë¡ľ
    -0.09
    iens
    -0.09
    عÙĩد
    -0.09
    俱ä¹IJéĥ¨
    -0.09
    äºĨåľ¨
    -0.08
    POSITIVE LOGITS
    think
    0.10
    æĪĸ个人
    0.09
    ings
    0.08
    ideon
    0.08
    ish
    0.08
    edly
    0.08
     halinde
    0.07
    åĨħçļĦ
    0.07
    leden
    0.07
    ossip
    0.07
    Activations Density 0.092%

    No Known Activations