© 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. 31482
    Prev
    Next
    INDEX
    Explanations

    constants, theory, systems

    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
    uard
    -0.08
     outlets
    -0.07
    ubern
    -0.07
     tá»ij
    -0.07
    quet
    -0.07
    gles
    -0.06
    ä¸ij
    -0.06
    maz
    -0.06
    lined
    -0.06
    docs
    -0.06
    POSITIVE LOGITS
    еди
    0.07
    rador
    0.07
    ::$
    0.07
    Ø®ÙĬ
    0.07
    csol
    0.07
    ÑĪÑĤÑĥ
    0.07
    ynamo
    0.07
    .rl
    0.06
    ophilia
    0.06
     Hyde
    0.06
    Activations Density 0.090%

    No Known Activations