© 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. 30644
    Prev
    Next
    INDEX
    Explanations

    each/every/chaque

    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
    itti
    -0.08
    ì¶
    -0.07
    ç¹ģ
    -0.07
    请åĬł
    -0.07
    WithValue
    -0.07
    itto
    -0.07
    erson
    -0.07
    mous
    -0.06
    illy
    -0.06
    å¼·åĬĽ
    -0.06
    POSITIVE LOGITS
    each
    0.09
    æ¯ı个
    0.09
     each
    0.08
    ê°ģ
    0.07
     Each
    0.07
    æ¯ıåĢĭ
    0.07
    麽
    0.07
    ä¸ĢèģĬ
    0.07
     chaque
    0.07
     '#'
    0.07
    Activations Density 0.040%

    No Known Activations