© 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. 10729
    Prev
    Next
    INDEX
    Explanations

    derivative wrt

    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
    æŃ¤æ¬¾
    -0.08
    idebar
    -0.08
    olib
    -0.07
     vét
    -0.07
    ÙĪرة
    -0.07
    écie
    -0.07
    Ùİاء
    -0.07
    gles
    -0.07
    lix
    -0.07
    ciel
    -0.07
    POSITIVE LOGITS
    åĺ±
    0.08
     derivative
    0.08
     differentiation
    0.08
    ivative
    0.07
     derivatives
    0.07
    .grad
    0.07
    changing
    0.07
     culpa
    0.07
     differentiated
    0.06
    åºĹéķ¿
    0.06
    Activations Density 0.025%

    No Known Activations