© 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. 38727
    Prev
    Next
    INDEX
    Explanations

    securing, holding, fixing

    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
    åĪĨ辨
    -0.07
     تÙģا
    -0.07
    æķĻåŃ¦æ°´å¹³
    -0.07
    ardy
    -0.06
    kses
    -0.06
    менов
    -0.06
     privileged
    -0.06
     abat
    -0.06
    privileged
    -0.06
    æ¸ħ鼶
    -0.06
    POSITIVE LOGITS
    çī¢åĽº
    0.20
    ç¨³åĽº
    0.15
    çī¢çī¢
    0.15
     binding
    0.13
     anchor
    0.13
    éĶļ
    0.13
    çī¢
    0.13
     chặt
    0.12
     firmly
    0.12
     bindings
    0.12
    Activations Density 0.261%

    No Known Activations