© 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. 60864
    Prev
    Next
    INDEX
    Explanations

    quality aluminium

    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
    ulich
    -0.08
    uhan
    -0.07
    åĽŀçŃĶéĩı
    -0.07
    ä¸ĵç²¾çī¹æĸ°
    -0.07
    rint
    -0.07
    utzt
    -0.07
    iket
    -0.07
    ErrorException
    -0.07
    人çľĭè¿ĩ
    -0.07
    å¾Ģäºĭ
    -0.07
    POSITIVE LOGITS
     tslint
    0.07
    ames
    0.07
    egna
    0.07
     Decompiled
    0.07
    -pic
    0.06
    agam
    0.06
     "`
    0.06
    övet
    0.06
    ç»Ħç»ĩç»ĵæŀĦ
    0.06
    agni
    0.06
    Activations Density 0.034%

    No Known Activations