© 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. 22744
    Prev
    Next
    INDEX
    Explanations

    romanized names with diacritics

    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
     <",
    -0.07
    åı£éķĩ
    -0.07
    çĤ¹å¤ļ
    -0.07
    mite
    -0.07
    ذب
    -0.07
    çİĦå¹»å°ı说
    -0.07
    ?’
    -0.06
    çķij
    -0.06
    åı£çļĦ
    -0.06
    åľ¨é¦Ļ港
    -0.06
    POSITIVE LOGITS
    à¸Ĺà¹Į
    0.07
    å¥Ķ
    0.07
    ä»ħæѤ
    0.06
     scarc
    0.06
    èĹIJ
    0.06
    ields
    0.06
    adrat
    0.06
    设计ä¸İ
    0.06
    ¿IJ
    0.06
    IELDS
    0.06
    Activations Density 0.043%

    No Known Activations