© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 15940
    Prev
    Next
    INDEX
    Explanations

    simple singularities

    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
    è¹Ń
    -0.07
    lit
    -0.07
    hal
    -0.06
    פ×ķ
    -0.06
    åģľäºĨ
    -0.06
    çļĦæ°Ķ
    -0.06
    åħħæ°Ķ
    -0.06
     creeping
    -0.06
     Magn
    -0.06
    liner
    -0.06
    POSITIVE LOGITS
    letin
    0.09
    éĶ»
    0.08
    ắm
    0.08
    otor
    0.08
    è¡Ŀ
    0.08
     brod
    0.07
    ÑĤеÑĤ
    0.07
    endom
    0.07
    endforeach
    0.07
     cristal
    0.07
    Activations Density 0.018%

    No Known Activations