© 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. 20701
    Prev
    Next
    INDEX
    Explanations

    difference between

    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
    ebed
    -0.08
    ä¹Łéļ¾
    -0.07
    ackson
    -0.07
    æĪijåIJ§
    -0.07
    alani
    -0.07
    ä½ķ为
    -0.07
    ợt
    -0.07
    è¿ĻçĤ¹
    -0.07
    ()."
    -0.06
    gai
    -0.06
    POSITIVE LOGITS
    ewire
    0.06
    -definition
    0.06
     volte
    0.06
    -over
    0.06
    (CC
    0.06
    æĪIJ为ä¸ĢåIJį
    0.06
    ими
    0.06
    uvia
    0.06
    iana
    0.06
    æĹ¢æĺ¯
    0.06
    Activations Density 0.181%

    No Known Activations