© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 64038
    Prev
    Next
    INDEX
    Explanations

    math expressions with values

    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
    alda
    -0.08
    deen
    -0.07
    outdir
    -0.07
    çŃł
    -0.07
    æµģæ°´
    -0.07
     codes
    -0.06
    aña
    -0.06
    èIJ½
    -0.06
    设为é¦ĸ页
    -0.06
    ium
    -0.06
    POSITIVE LOGITS
    è¶ĭäºİ
    0.10
    éļıçĿĢ
    0.10
    lim
    0.10
     conver
    0.09
     converge
    0.09
     eventualmente
    0.08
    éļıçĿĢæŶéĹ´çļĦæݨ移
    0.08
    éļıåľ°
    0.08
    ä¹Łè¶ĬæĿ¥è¶Ĭ
    0.08
    ipl
    0.08
    Activations Density 0.010%

    No Known Activations