© 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. 56869
    Prev
    Next
    INDEX
    Explanations

    This introduces a description

    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
    åIJĪåIJĮæŶ
    -0.09
    umbre
    -0.08
    uable
    -0.08
    cente
    -0.08
    avel
    -0.08
    aler
    -0.07
    λάÏĩιÏĥ
    -0.07
    hip
    -0.07
    /from
    -0.07
    orer
    -0.07
    POSITIVE LOGITS
    代人
    0.07
    æĽ´æĸ°äºİ
    0.07
     notwithstanding
    0.06
    ä¸įçķĻ
    0.06
    åħ¶ä¸Ńæľī
    0.06
    à¹ģà¸Ļ
    0.06
    leit
    0.06
    íĥ
    0.06
     information
    0.06
    ika
    0.06
    Activations Density 0.361%

    No Known Activations