© 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. 29401
    Prev
    Next
    INDEX
    Explanations

    historian or historical events

    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
    amil
    -0.07
    oren
    -0.07
    apesh
    -0.07
    imum
    -0.07
    phin
    -0.07
    å½¢èī²
    -0.07
    ansi
    -0.07
    atum
    -0.07
    çĶŁçIJĨ
    -0.07
     Willis
    -0.06
    POSITIVE LOGITS
    åĴĮåİĨåı²
    0.10
    æľĿ代
    0.09
    åĴĮæĶ¿æ²»
    0.09
     events
    0.08
     history
    0.08
    åı²
    0.08
    æİĮ
    0.08
    æĤłä¹ħçļĦ
    0.08
    éķ¿æ²³
    0.08
    åİĨåı²çļĦ
    0.08
    Activations Density 0.052%

    No Known Activations