© 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. 56829
    Prev
    Next
    INDEX
    Explanations

    quadratic and cubic equations

    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
    chaft
    -0.10
    ivo
    -0.10
    edly
    -0.09
    liness
    -0.09
    ////////////////////////////////////////////////////
    -0.08
    ych
    -0.08
    ings
    -0.08
    âķIJâķIJâķIJâķIJ
    -0.08
    ighting
    -0.08
    ações
    -0.08
    POSITIVE LOGITS
    ly
    0.09
    ité
    0.08
    ../../../
    0.08
    zelfde
    0.07
    town
    0.07
    /oct
    0.07
    ity
    0.07
    écr
    0.07
    -linear
    0.07
    ens
    0.06
    Activations Density 0.005%

    No Known Activations