© 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. 20684
    Prev
    Next
    INDEX
    Explanations

    conversion or step in pathway

    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
    èĩªçĦ¶ä¹Ł
    -0.07
    ellent
    -0.06
     Telefon
    -0.06
    èĩªçĦ¶ä¼ļ
    -0.06
    èĮĹ
    -0.06
     reprodu
    -0.06
    æ®ī
    -0.06
    ILO
    -0.06
    ç¦Ħ
    -0.06
    æ´
    -0.06
    POSITIVE LOGITS
    Conversion
    0.10
    转åĮĸ
    0.10
     Convert
    0.10
     convert
    0.10
     conversions
    0.10
    convert
    0.10
     Conversion
    0.10
     conversion
    0.10
    conversion
    0.10
    Convert
    0.10
    Activations Density 0.038%

    No Known Activations