© 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. 3644
    Prev
    Next
    INDEX
    Explanations

    both...and

    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
    æĬĬåŃ¦ä¹ł
    -0.07
    åľ¨ä¸į
    -0.07
    çŃĶ主
    -0.07
    ึà¸ĩ
    -0.07
    .tc
    -0.07
    isy
    -0.06
    èµĦ产交æĺĵ
    -0.06
    iecz
    -0.06
    è§Ħå®ļçļĦåħ¶ä»ĸ
    -0.06
    iak
    -0.06
    POSITIVE LOGITS
    ä¸Ģæĺ¯
    0.09
    ä¸Ģæĺ¯è¦ģ
    0.08
    istan
    0.07
    à¹Ĥà¸Ħ
    0.07
    th
    0.07
     ÑĢазвод
    0.06
    apest
    0.06
    çī©çIJĨ
    0.06
    engo
    0.06
    cape
    0.06
    Activations Density 0.153%

    No Known Activations