© 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. 16316
    Prev
    Next
    INDEX
    Explanations

    0000 sequences

    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
    ड़
    -0.07
    åħīæĺ¯
    -0.07
    ên
    -0.07
    ewa
    -0.07
    istrate
    -0.07
    åŁİåĮĹ
    -0.07
    pac
    -0.06
    Ñģи
    -0.06
    setting
    -0.06
    ħ
    -0.06
    POSITIVE LOGITS
    urred
    0.07
    éľŀ
    0.07
    |string
    0.07
    |RF
    0.07
    vanced
    0.07
    arer
    0.07
    |array
    0.06
    è°·
    0.06
    refs
    0.06
    æīĵå¼Ģæīĭæľº
    0.06
    Activations Density 0.026%

    No Known Activations