© 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. 26832
    Prev
    Next
    INDEX
    Explanations

    a/an followed by noun

    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
    rong
    -0.07
     Pedi
    -0.06
    ewan
    -0.06
    ÙĨاس
    -0.06
    sockopt
    -0.06
    Ä·
    -0.06
    次äºİ
    -0.06
    uestos
    -0.06
    对åİŁåijĬ
    -0.06
    usus
    -0.06
    POSITIVE LOGITS
     qualsiasi
    0.08
    yo
    0.08
     properly
    0.08
     magát
    0.08
    erial
    0.08
    åħ¸åŀĭçļĦ
    0.08
     typical
    0.07
    缴è¾ĸå¸Ĥ
    0.07
    æ´Ľå¤«
    0.07
    ä»»ä½ķäºĭæĥħ
    0.07
    Activations Density 0.168%

    No Known Activations