© 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. 15016
    Prev
    Next
    INDEX
    Explanations

    `holding`, `decide`, `centrally`, `cancelling`

    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
    onga
    -0.09
    ukka
    -0.09
    aho
    -0.08
    anio
    -0.08
    /TR
    -0.08
    å®ħéħį
    -0.07
    éĤ£æŶçļĦ
    -0.07
    .Helper
    -0.07
    -&
    -0.07
    presso
    -0.07
    POSITIVE LOGITS
    æľīä¸ĭåĪĹæĥħå½¢ä¹ĭä¸ĢçļĦ
    0.09
    æľīä¸ĭåĪĹ
    0.09
    为éĿŀ
    0.08
    ä¸įåIJĮæŶ
    0.08
    ãģ©ãģĨãģĹãģ¦ãĤĤ
    0.07
    åīį款
    0.07
    åıijçĶŁéĩį大
    0.07
    æŀľçľŁ
    0.07
     accidentally
    0.07
    è¿ŀç»Ń
    0.07
    Activations Density 0.013%

    No Known Activations