© 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. 40111
    Prev
    Next
    INDEX
    Explanations

    coordinates and method calls

    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
    tle
    -0.07
    æĺ¯ä¸Ģç§įéĿŀ常
    -0.07
    )(*
    -0.06
    æľŁåĨħ
    -0.06
    à¶Ńà·Ĭ
    -0.06
    çŃī大åŀĭ
    -0.06
    coe
    -0.06
     sekali
    -0.06
    Ĵ
    -0.05
    èĤļçļ®
    -0.05
    POSITIVE LOGITS
    ardini
    0.08
    .Exit
    0.08
    poste
    0.08
    ndern
    0.07
     chau
    0.07
    åĴĮåĨħ容
    0.07
    logfile
    0.07
    intes
    0.07
    iculty
    0.07
    iliate
    0.07
    Activations Density 0.010%

    No Known Activations