© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42262
    Prev
    Next
    INDEX
    Explanations

    tensor related concepts

    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
    gers
    -0.08
    temps
    -0.08
    ëģĶ
    -0.08
    ²
    -0.07
    kker
    -0.07
    tim
    -0.07
    s
    -0.07
    nings
    -0.07
    صÙĬد
    -0.07
    ÅĻenÃŃ
    -0.07
    POSITIVE LOGITS
    oidal
    0.10
    esis
    0.09
    onomy
    0.09
    aurus
    0.09
    ized
    0.08
    rone
    0.08
    па
    0.08
    ë§ģ
    0.08
    ORM
    0.08
    izable
    0.08
    Activations Density 0.003%

    No Known Activations