© 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. 32420
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions in code

    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
    ponge
    -0.07
    mime
    -0.06
    urut
    -0.06
    èĸĦçļĦ
    -0.06
     outskirts
    -0.06
    Ïĩε
    -0.06
    åĨįä¸ī
    -0.06
    é¾IJ
    -0.06
     pojed
    -0.06
    mios
    -0.06
    POSITIVE LOGITS
    linear
    0.09
    æĭŁåIJĪ
    0.08
     fitted
    0.08
     fitting
    0.08
    -linear
    0.07
    áŀ¶áŀĻ
    0.07
    线æĢ§
    0.07
     linear
    0.07
    onton
    0.07
    Inverse
    0.07
    Activations Density 0.017%

    No Known Activations