© 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. 31706
    Prev
    Next
    INDEX
    Explanations

    remove or removal

    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
    çī¹èģĺ
    -0.08
     Agu
    -0.07
    ãģ«ãģªãĤĮãĤĭ
    -0.07
    ä¸įåıĹ
    -0.07
    _embed
    -0.06
     actualidad
    -0.06
     agu
    -0.06
    ÅĪa
    -0.06
    åħĭæľįåĽ°éļ¾
    -0.06
     relaxed
    -0.06
    POSITIVE LOGITS
     khá»ıi
    0.12
    è¿ŀåIJĮ
    0.09
     Removes
    0.09
    è¾Ľè¾Ľèĭ¦
    0.08
    å¤ļä½ĻçļĦ
    0.08
     redund
    0.08
     lasciando
    0.08
    (remove
    0.08
    èµĸ以
    0.08
     removal
    0.08
    Activations Density 0.112%

    No Known Activations