© 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. 64342
    Prev
    Next
    INDEX
    Explanations

    Taylor expansion, derivatives, linear quadratic approach

    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
    egers
    -0.09
    åIJ¸åħ¥
    -0.08
    acios
    -0.08
    .fromString
    -0.08
    FromString
    -0.08
    imento
    -0.08
    avers
    -0.08
    شار
    -0.07
    貫
    -0.07
    åIJĥä¸ľè¥¿
    -0.07
    POSITIVE LOGITS
     Taylor
    0.07
     approximation
    0.07
    _UPDATED
    0.06
    æ³°åĭĴ
    0.06
    è¡·å¿ĥçļĦ
    0.06
    zept
    0.06
     vi
    0.06
    ke
    0.06
    çĺ¸
    0.06
    _ctxt
    0.06
    Activations Density 0.007%

    No Known Activations