© 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. 46201
    Prev
    Next
    INDEX
    Explanations

    repeatedly or successively

    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
    vende
    -0.08
    äºīå½ĵ
    -0.07
    èĮĥ
    -0.07
    è£ħåľ¨
    -0.07
    ackbar
    -0.07
    Window
    -0.07
    ä¸Ģæī¶
    -0.07
    ovor
    -0.06
    æľ¬è¯¥
    -0.06
    éĸĵãģ«
    -0.06
    POSITIVE LOGITS
     repeatedly
    0.19
     successive
    0.16
    å¤ļ次
    0.15
     recursively
    0.15
     iter
    0.14
    è¿Ń代
    0.14
     progressively
    0.14
    éĢIJ级
    0.13
     iterative
    0.13
    éĵ¾
    0.13
    Activations Density 0.089%

    No Known Activations