© 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. 2593
    Prev
    Next
    INDEX
    Explanations

    achievements and dimensions

    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
    ?]
    -0.09
    UNET
    -0.08
    eness
    -0.08
    è°ģçŁ¥éģĵ
    -0.08
    æī©å±ķèµĦæĸĻ
    -0.08
    以ä¸Ĭå°±æĺ¯åħ³äºİ
    -0.08
     eyl
    -0.07
    amalla
    -0.07
     모ë¦Ħ
    -0.07
    olem
    -0.07
    POSITIVE LOGITS
     voici
    0.08
    æľī以ä¸ĭ
    0.08
    .First
    0.07
    以ä¸ĭæĺ¯
    0.07
    aping
    0.07
     First
    0.06
    agin
    0.06
     Voici
    0.06
    Ñļ
    0.06
    以ä¸ĭåĩłä¸ªæĸ¹éĿ¢
    0.06
    Activations Density 0.130%

    No Known Activations