© 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. 49993
    Prev
    Next
    INDEX
    Explanations

    sentence endings

    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
    è§ģæѤ
    -0.08
    istingu
    -0.07
    chap
    -0.07
    attes
    -0.07
    çĹħæĥħåĪĨæŀIJ
    -0.07
    æī©å±ķèµĦæĸĻ
    -0.07
    atric
    -0.07
    chal
    -0.07
    нÑĥÑģ
    -0.07
    为ä»Ģä¹Īåij¢
    -0.07
    POSITIVE LOGITS
    velle
    0.07
    æ·»
    0.06
    ohen
    0.06
    emia
    0.06
    pje
    0.06
    ignum
    0.06
    ehand
    0.06
    orden
    0.06
     anci
    0.06
    shortcut
    0.06
    Activations Density 0.021%

    No Known Activations