© 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. 39671
    Prev
    Next
    INDEX
    Explanations

    toward this / towards this

    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
    ály
    -0.08
    пози
    -0.07
    unden
    -0.07
    è¦ģæĥ³
    -0.07
    posito
    -0.07
    ingang
    -0.07
     викоÑĢ
    -0.07
    à§įà¦Ł
    -0.07
    chet
    -0.07
     entière
    -0.07
    POSITIVE LOGITS
    å¾Ģ常ä¸Ģæł·
    0.10
    stig
    0.09
    ä½ķæĸ¹
    0.09
    ness
    0.09
    sWith
    0.08
    ä»ĸ表示
    0.08
    nees
    0.08
    å²ģçļĦåŃ©åŃIJ
    0.08
    æŀģäºĨ
    0.08
    纵深
    0.07
    Activations Density 0.013%

    No Known Activations