© 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. 11731
    Prev
    Next
    INDEX
    Explanations

    solution, software, designed, possible

    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
    edd
    -0.08
    éľĢè¦ģæıIJåīį
    -0.08
    åľ°ä¹ħ
    -0.07
    à¤Ĥà¤Ĺ
    -0.07
    naan
    -0.07
    quo
    -0.07
    è¯ķè¡Į
    -0.07
    èĬĴ
    -0.07
    ÐĿÐł
    -0.07
    edy
    -0.06
    POSITIVE LOGITS
    oke
    0.08
    éĻ¤äºĨ
    0.07
    以åĨħ
    0.07
    ä¸įåıªæĺ¯
    0.07
    ä¸ĢåĪ°
    0.07
     izol
    0.06
    æľīä¸Ģå¥Ĺ
    0.06
    主è¦ģå°±æĺ¯
    0.06
    ä¸ĢæĶ¹
    0.06
    LETTE
    0.06
    Activations Density 0.004%

    No Known Activations