© 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. 14158
    Prev
    Next
    INDEX
    Explanations

    dequeue, get, or recover

    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
    اÙģÙĬ
    -0.09
    ardini
    -0.08
    好åIJİ
    -0.08
    OnInit
    -0.08
    [section
    -0.07
    ฬ
    -0.07
     parlam
    -0.07
    /scripts
    -0.07
    åĬłåħ¥ä¹¦çŃ¾
    -0.07
    åĴĮä¸į足
    -0.07
    POSITIVE LOGITS
    OrNull
    0.07
    s
    0.07
     khá»ıi
    0.07
     оÑĩеÑĢед
    0.07
    æľ¬åľºæ¯ĶèµĽ
    0.06
    ovich
    0.06
    Expired
    0.06
    uhu
    0.06
    ạc
    0.06
     оÑĤÑĤ
    0.06
    Activations Density 0.005%

    No Known Activations