© 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. 11929
    Prev
    Next
    INDEX
    Explanations

    discretionary trusts in his sights

    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
    ewa
    -0.08
    agro
    -0.07
    SetValue
    -0.07
    ówka
    -0.07
    åıĪæľīä»Ģä¹Ī
    -0.07
    代çIJĨæľīéĻIJåħ¬åı¸
    -0.07
    ×IJ×ķת
    -0.07
    åı¦ä¸Ģè¾¹
    -0.07
    WEBPACK
    -0.07
     Jehovah
    -0.07
    POSITIVE LOGITS
     ÑıкобÑĭ
    0.09
    ä»ĸ们认为
    0.09
    à¹Ħวà¹ī
    0.08
    ç¡®æľī
    0.08
    ä»ĸ们è¿ĺ
    0.08
    çļĦç¡®
    0.07
    ç¡®
    0.07
     à¹Ħวà¹ī
    0.07
     indeed
    0.07
    ç¡®å®ŀæĺ¯
    0.07
    Activations Density 1.134%

    No Known Activations