© 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. 27720
    Prev
    Next
    INDEX
    Explanations

    past events and history

    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
    ered
    -0.10
    avance
    -0.09
    æĹĹé¼ĵ
    -0.09
    erÃŃa
    -0.09
    esten
    -0.09
    UnderTest
    -0.09
    ecter
    -0.08
    macher
    -0.08
    ãģ£ãģĵãģĨ
    -0.08
    erable
    -0.08
    POSITIVE LOGITS
    ime
    0.11
    åĴĮæľªæĿ¥
    0.10
    ebin
    0.10
    /current
    0.09
    imes
    0.08
    oral
    0.08
    åĴĮåīį
    0.08
    OrDefault
    0.07
    éķ¿æ²³
    0.07
    iche
    0.07
    Activations Density 0.036%

    No Known Activations