© 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. 33595
    Prev
    Next
    INDEX
    Explanations

    cooling down processes

    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
    åįıè°ĥ
    -0.07
    åįķä½ĵ
    -0.06
     Comp
    -0.06
    comp
    -0.06
    olit
    -0.06
    æºIJ
    -0.06
    Äĥng
    -0.06
    ottes
    -0.06
    ä¾
    -0.06
     egz
    -0.06
    POSITIVE LOGITS
    æħ¢æħ¢åľ°
    0.10
     dần
    0.10
    æħ¢æħ¢
    0.10
    สà¸Ļิà¸Ĺ
    0.09
    æħ¢æħ¢çļĦ
    0.09
    ç¼ĵç¼ĵçļĦ
    0.09
    aixa
    0.08
    ä¸ĢçĤ¹ä¸ĢçĤ¹
    0.08
    ardown
    0.08
    uish
    0.08
    Activations Density 0.017%

    No Known Activations