© 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. 20729
    Prev
    Next
    INDEX
    Explanations

    plating

    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
    æĭ¶
    -0.08
    ÙĪÙĬÙĦ
    -0.08
    bé
    -0.08
    秫
    -0.08
    æ¥Ķ
    -0.08
     stom
    -0.07
    å¯Ħ宿
    -0.07
    istet
    -0.07
    æł¼æĭīæĸ¯
    -0.07
    mlx
    -0.07
    POSITIVE LOGITS
     deposits
    0.10
     deposit
    0.10
    çĶµéķĢ
    0.09
     deposited
    0.09
    éĵľ
    0.08
     copper
    0.08
    éķĢ
    0.08
     deposition
    0.08
     Depos
    0.08
     Deposit
    0.08
    Activations Density 0.016%

    No Known Activations