© 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. 64350
    Prev
    Next
    INDEX
    Explanations

    inner join or inner workings

    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
    efully
    -0.08
    خاÙĨÙĩ
    -0.08
    ting
    -0.08
     latter
    -0.08
    illons
    -0.08
    ়
    -0.08
    eful
    -0.07
     Tulis
    -0.07
    .sharedInstance
    -0.07
    ynchronously
    -0.07
    POSITIVE LOGITS
    halb
    0.13
    ness
    0.10
    most
    0.10
    /out
    0.09
    urance
    0.09
    (er
    0.09
    stadt
    0.09
    оÑĢа
    0.09
     workings
    0.08
    -sama
    0.08
    Activations Density 0.008%

    No Known Activations