© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21526
    Prev
    Next
    INDEX
    Explanations

    * or ## or . followed by a space

    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
    笹
    -0.07
    sex
    -0.06
    him
    -0.06
    leep
    -0.06
    urende
    -0.06
    zel
    -0.06
    lest
    -0.06
    å·´æĭī
    -0.06
    ä¸ŃçļĦä¸Ģ
    -0.06
    à§ĭধ
    -0.06
    POSITIVE LOGITS
    缸è¾ħ缸æĪIJ
    0.11
    ä¸įåı¯æĢĿè®®
    0.10
    两åѦä¸Ģåģļ
    0.09
    身临åħ¶å¢ĥ
    0.09
    åį«çĶŁç»Ħç»ĩ
    0.09
    ."]
    0.09
    åĭĩå¾Ģ缴åīį
    0.08
    .','
    0.08
    ä¼ĹæīĢåij¨çŁ¥
    0.08
    æĸ°åĬłåĿ¡
    0.08
    Activations Density 0.585%

    No Known Activations