© 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. 22616
    Prev
    Next
    INDEX
    Explanations

    problems shortcomings found in new products

    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
     assieme
    -0.08
    Though
    -0.08
     Whilst
    -0.08
    çĶµè®¯
    -0.08
    ä¹Ī
    -0.08
    ÙĥÙIJ
    -0.08
    retty
    -0.07
    çŃ¾å®ļ
    -0.07
     пÑĢоÑĩиÑħ
    -0.07
    ä¸įçĶļ
    -0.07
    POSITIVE LOGITS
    0.19
    0.08
    .Txt
    0.07
    æĺ¾çĿĢ
    0.07
     compreh
    0.07
    ừ
    0.07
     decis
    0.06
    主è¦ģæĺ¯æĮĩ
    0.06
    .rf
    0.06
     decisive
    0.06
    Activations Density 1.657%

    No Known Activations