© 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. 22219
    Prev
    Next
    INDEX
    Explanations

    algebraic terms

    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
    ÄįÃŃ
    -0.07
    æ´Ľä¼Ĭ
    -0.07
    vania
    -0.06
    è¿ĩ好
    -0.06
    WD
    -0.06
    CA
    -0.06
    b
    -0.06
    áĥĶáĥĵ
    -0.06
     Cano
    -0.06
    :list
    -0.06
    POSITIVE LOGITS
     Performing
    0.07
    _TERM
    0.07
    .nr
    0.07
    ptica
    0.07
    à¸ŀà¸ĩ
    0.07
    clamation
    0.07
    @hotmail
    0.07
    æĭ¬
    0.06
    olynomial
    0.06
    iraz
    0.06
    Activations Density 0.020%

    No Known Activations