© 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. 42529
    Prev
    Next
    INDEX
    Explanations

    java code examples

    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
    ÙĤÙĬÙĤ
    -0.09
    å¸ĮæľĽå¯¹æĤ¨
    -0.09
    exter
    -0.09
    ãĤ¥
    -0.08
    ovan
    -0.08
    éľĨ
    -0.08
    ../../../
    -0.08
    ools
    -0.08
    à¸Ļà¹Į
    -0.08
    еÑĩÑĮ
    -0.08
    POSITIVE LOGITS
    缸è¾ħ缸æĪIJ
    0.11
    åħ¢åħ¢ä¸ļä¸ļ
    0.10
    æ¯Ľæ³½ä¸ľ
    0.09
    s
    0.09
    ä¼ĹæīĢåij¨çŁ¥
    0.09
    åĭĩå¾Ģ缴åīį
    0.09
    æĸ°åĬłåĿ¡
    0.09
    俱ä¹IJéĥ¨
    0.08
    æ¯Ľæ³½ä¸ľæĢĿæĥ³
    0.08
    两åѦä¸Ģåģļ
    0.08
    Activations Density 0.039%

    No Known Activations