© 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. 3948
    Prev
    Next
    INDEX
    Explanations

    scientific measurements

    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
    fab
    -0.08
    å°¤åħ¶æĺ¯
    -0.07
    çī¹åĪ«æĺ¯
    -0.07
    å°Ĩæľī
    -0.07
    pecially
    -0.07
    ä¸įéĻIJ
    -0.07
     ith
    -0.06
    iak
    -0.06
    æľŁéĻIJåĨħ
    -0.06
    ä½ķåĨµ
    -0.06
    POSITIVE LOGITS
     reportedly
    0.14
    å®ĺæĸ¹
    0.09
    æį®æĬ¥éģĵ
    0.09
    ombe
    0.08
     addirittura
    0.08
    æį®æĤī
    0.08
    ãģªãĤĵãģ¨
    0.08
    æį®è¯´
    0.08
     reported
    0.08
     official
    0.08
    Activations Density 0.006%

    No Known Activations