© 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. 62748
    Prev
    Next
    INDEX
    Explanations

    45

    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
    è·»
    -0.07
    оз
    -0.06
    麾
    -0.06
    禦
    -0.06
    èĸĦ
    -0.06
     aside
    -0.06
    ائ
    -0.06
    etts
    -0.06
    ellen
    -0.06
    åľ¨ä»ĬåIJİ
    -0.06
    POSITIVE LOGITS
    ï¸ı
    0.10
    âĸĪ
    0.08
    htag
    0.08
    erval
    0.08
    çıĬ
    0.08
    imbang
    0.08
    esso
    0.08
    ewire
    0.08
    inson
    0.08
    erti
    0.08
    Activations Density 0.115%

    No Known Activations