© 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. 43304
    Prev
    Next
    INDEX
    Explanations

    solar, heat, temperature

    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
     micron
    -0.07
    ringe
    -0.07
    oth
    -0.07
     blinded
    -0.07
     tightening
    -0.07
    gift
    -0.07
     COMPR
    -0.07
    بÙĬب
    -0.07
     tighten
    -0.07
    æµģ水线
    -0.07
    POSITIVE LOGITS
    åıįå°Ħ
    0.09
     solar
    0.09
     daytime
    0.08
     ë³µìĤ¬
    0.08
    çļĦçĥŃéĩı
    0.08
    èĵĦ
    0.08
    ä¸įéĢı
    0.08
    bedo
    0.08
     ÑĢаÑģка
    0.08
     adi
    0.08
    Activations Density 0.009%

    No Known Activations