© 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. 56702
    Prev
    Next
    INDEX
    Explanations

    product, unit, claim, score, amount, object, count

    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
    notated
    -0.09
    ï¸İ
    -0.08
    sembl
    -0.08
    ÙIJÙij
    -0.08
    imensional
    -0.07
    åŃIJéĩĮ
    -0.07
    mbH
    -0.07
    à¹Ģà¸Ķิม
    -0.07
    Ùij
    -0.07
    gether
    -0.07
    POSITIVE LOGITS
    hurt
    0.08
    osate
    0.08
    ÑĢÑıдо
    0.07
    клеи
    0.07
    еÑģÑĤа
    0.07
    hun
    0.07
    ÑģовеÑģÑĤ
    0.07
    promo
    0.07
    ÃŃze
    0.07
    ãĥĥãĥijãĥ¼
    0.07
    Activations Density 0.383%

    No Known Activations