© 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. 15302
    Prev
    Next
    INDEX
    Explanations

    numbers and citations

    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
    åīįå¾Į
    -0.08
    åīįåIJİ
    -0.08
    atted
    -0.07
     benne
    -0.07
    apg
    -0.07
     bele
    -0.07
     chunks
    -0.07
    +offset
    -0.06
    è¡Įä¸ļåĨħ
    -0.06
     Kond
    -0.06
    POSITIVE LOGITS
    èĢĮ论
    0.08
    éĢļåĪĻ
    0.07
    enary
    0.07
    éĻħ
    0.07
    êµ
    0.06
    ç»ıçIJĨ人
    0.06
    stor
    0.06
     dreaded
    0.06
    æĶ»åĿļæĪĺ
    0.06
     st
    0.06
    Activations Density 0.062%

    No Known Activations