© 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. 18040
    Prev
    Next
    INDEX
    Explanations

    sealing or seals

    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
     اÙĦÙħسÙĦ
    -0.07
    veal
    -0.07
    ordon
    -0.07
    æĸĽ
    -0.07
     démarr
    -0.07
    vene
    -0.07
    anaf
    -0.06
    ENDOR
    -0.06
    loads
    -0.06
    å°ijèµ°
    -0.06
    POSITIVE LOGITS
     sealing
    0.12
     seals
    0.11
    ä¸į严
    0.10
     seal
    0.10
    å¯Ĩå°ģ
    0.10
    ä¸įæ¼ı
    0.09
     integrity
    0.09
    åı£æ°´
    0.09
     Integrity
    0.08
    éĸī
    0.08
    Activations Density 0.061%

    No Known Activations