© 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. 28467
    Prev
    Next
    INDEX
    Explanations

    two words

    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
    icale
    -0.07
     presto
    -0.07
    ä¹Łç½¢
    -0.07
    ç±ģ
    -0.07
    richText
    -0.07
    strand
    -0.07
    adari
    -0.07
    Dou
    -0.07
    -about
    -0.07
    istros
    -0.07
    POSITIVE LOGITS
    å¹´å¹´
    0.08
    imiter
    0.07
    ç¶ļãģı
    0.07
     Frist
    0.07
    æ¯ıå¹´éĥ½
    0.06
    oded
    0.06
    æ¯ıå¹´éĥ½ä¼ļ
    0.06
    frist
    0.06
    ode
    0.06
    olen
    0.06
    Activations Density 0.061%

    No Known Activations