© 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. 23327
    Prev
    Next
    INDEX
    Explanations

    documentation snippets

    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
    .insertBefore
    -0.08
    ardash
    -0.08
    Idle
    -0.08
    éĢļè¿ĩ以ä¸Ĭ
    -0.08
    éļ¾ä»¥å¿ĺæĢĢ
    -0.07
    以ä¸ĬåĨħ容
    -0.07
    对ä¸Ĭè¿°
    -0.07
    oons
    -0.07
    _TIMESTAMP
    -0.07
    ä¸įä»ħåľ¨
    -0.07
    POSITIVE LOGITS
    éĺ´
    0.06
    ">*</
    0.06
     mainly
    0.06
     zero
    0.06
    è¨Ģ
    0.06
     '*'
    0.06
     gedacht
    0.06
    å¿ħå°Ĩ
    0.06
    ç§ij
    0.06
    çIJ
    0.06
    Activations Density 0.514%

    No Known Activations