© 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. 40262
    Prev
    Next
    INDEX
    Explanations

    special exception for license

    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
    sein
    -0.08
    aise
    -0.08
    лÑĮкÑĥ
    -0.08
    èĬĤ
    -0.08
    asih
    -0.07
    اعد
    -0.07
    ÑģÑģа
    -0.07
    rik
    -0.07
    ave
    -0.07
    ideon
    -0.07
    POSITIVE LOGITS
     sublicense
    0.10
     Affero
    0.08
    éĢĤçĶ¨æ³ķå¾ĭ
    0.07
     conspic
    0.07
     Redistributions
    0.07
     Heidel
    0.07
    /bower
    0.07
     sublic
    0.07
    åIJįåĪĹ
    0.07
    åīį款
    0.07
    Activations Density 0.920%

    No Known Activations