© 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. 56468
    Prev
    Next
    INDEX
    Explanations

    end of sentences or clauses

    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
    ymo
    -0.08
    etz
    -0.08
     маÑģÑĪÑĤа
    -0.08
    大çĹħ
    -0.07
    eten
    -0.07
    æĬĬæīĢæľīçļĦ
    -0.07
    ä»ĸè¿ĺæĺ¯
    -0.07
    ini
    -0.07
    大é£İ
    -0.07
    داد
    -0.07
    POSITIVE LOGITS
    åĪĨæŀIJ
    0.09
    analysis
    0.08
    åĪĨæŀIJä¸İ
    0.08
    è¦ģæĪij
    0.08
    ä¹į
    0.08
    phia
    0.08
     analys
    0.08
    åħ·ä½ĵåĪĨæŀIJ
    0.07
    åĪĨæŀIJåıĬ
    0.07
     analysis
    0.07
    Activations Density 0.023%

    No Known Activations