© 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. 8325
    Prev
    Next
    INDEX
    Explanations

    backup and reserve

    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
    åIJijèį£
    -0.09
    /ion
    -0.08
    è¿ĶåĽŀ顶éĥ¨
    -0.08
    è¿ĻèĪ¬
    -0.08
    ventus
    -0.08
    mith
    -0.08
    regor
    -0.08
     volna
    -0.08
    пла
    -0.08
     ÑģквозÑĮ
    -0.08
    POSITIVE LOGITS
    å¤ĩçĶ¨
    0.09
    以å¤ĩ
    0.08
    à¹Ħวà¹ī
    0.08
    èµ·è§ģ
    0.07
     reserve
    0.07
    ä¸ĩä¸Ģ
    0.06
    ary
    0.06
    å¤ĩ份
    0.06
    åĤĻ
    0.06
    à¹Ħวà¹īà¹ĥà¸Ļ
    0.06
    Activations Density 0.031%

    No Known Activations