© 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. 33325
    Prev
    Next
    INDEX
    Explanations

    file extensions and code formats

    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
    :],
    -0.10
    serter
    -0.09
    ungk
    -0.08
    ä¹ĭéģĵ
    -0.08
    ALO
    -0.07
    å¥ı
    -0.07
    mig
    -0.07
    æĬĬäºĭæĥħ
    -0.07
    eit
    -0.07
    åħ¶éģĵ
    -0.07
    POSITIVE LOGITS
    .gz
    0.13
    .bz
    0.08
    .au
    0.08
    æł¼å¼ıçļĦ
    0.07
    .br
    0.07
    .erb
    0.07
    chner
    0.06
    utral
    0.06
    ç¾İä¸Ń
    0.06
     Worth
    0.06
    Activations Density 0.305%

    No Known Activations