© 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. 62628
    Prev
    Next
    INDEX
    Explanations

    cubic extension or order

    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
    æĶ¾çŁ¢
    -0.08
    çĻ¾å·Ŀ
    -0.08
    heets
    -0.08
    aufnahme
    -0.07
    abei
    -0.07
    ä¹ħèĢĮä¹ħä¹ĭ
    -0.07
    бели
    -0.07
    вÑĪими
    -0.07
    osaic
    -0.07
    ctr
    -0.07
    POSITIVE LOGITS
    illion
    0.08
    åıĬ以ä¸ĭ
    0.07
    resse
    0.07
    åĴĮäºĮ
    0.07
    engage
    0.06
    ä¸Ģä½ĵæľº
    0.06
    Uns
    0.06
     Vig
    0.06
    master
    0.06
    enary
    0.06
    Activations Density 0.001%

    No Known Activations