© 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. 11995
    Prev
    Next
    INDEX
    Explanations

    steady state

    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
    èĤ¡
    -0.08
    ifel
    -0.07
    å²Ĥ
    -0.07
    atismo
    -0.07
    _EXPORT
    -0.07
    _PUSH
    -0.06
    丼
    -0.06
    éĢĨ
    -0.06
    ä»İå°ıåĪ°å¤§
    -0.06
    <&
    -0.06
    POSITIVE LOGITS
     settles
    0.11
     settle
    0.09
    稳å®ļ
    0.09
     settling
    0.09
     stable
    0.09
     after
    0.09
    è°ĥæķ´åIJİ
    0.08
    çļĦ稳å®ļ
    0.08
     Sett
    0.08
     settled
    0.08
    Activations Density 0.047%

    No Known Activations