© 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. 32572
    Prev
    Next
    INDEX
    Explanations

    growth and development

    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
    atura
    -0.09
    prech
    -0.09
    äºĨäºĭ
    -0.08
    _MALLOC
    -0.08
    ราษà¸İ
    -0.08
    schlag
    -0.08
    à¹Īมืà¸Ń
    -0.08
    εÏħ
    -0.08
    aments
    -0.08
    /il
    -0.08
    POSITIVE LOGITS
    ths
    0.08
    ings
    0.08
    壮大çļĦ
    0.08
    ish
    0.08
    壮大
    0.08
     pesat
    0.07
    ève
    0.07
    orgeous
    0.07
    /de
    0.07
     accustomed
    0.07
    Activations Density 0.057%

    No Known Activations