© 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. 25778
    Prev
    Next
    INDEX
    Explanations

    pattern, firefighter, game, math, sunburn, Voldemort

    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
    onte
    -0.08
    áŀ»
    -0.07
    licted
    -0.07
    icaid
    -0.07
    åĴĮå¹³
    -0.07
    onie
    -0.07
    onia
    -0.07
    ouncing
    -0.07
     samt
    -0.06
    ä¸īä¸ĸ
    -0.06
    POSITIVE LOGITS
    çĶļèĩ³è¿ŀ
    0.11
    çŃīçŃī
    0.11
    çĶļèĩ³äºİ
    0.09
    çĶļèĩ³è¿ĺ
    0.09
     etc
    0.08
    ä¹Łç½¢
    0.08
     dokonce
    0.08
    çĶļèĩ³åľ¨
    0.08
    çĶļèĩ³
    0.08
     maybe
    0.08
    Activations Density 0.612%

    No Known Activations