© 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. 44897
    Prev
    Next
    INDEX
    Explanations

    dividing or separating into parts

    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
    ESTA
    -0.07
    KR
    -0.07
     ÑģÑĨеп
    -0.07
    rex
    -0.07
    ml
    -0.07
    inya
    -0.06
    æľįåĬ¡å¹³åı°
    -0.06
    avel
    -0.06
    idium
    -0.06
    esis
    -0.06
    POSITIVE LOGITS
     divides
    0.10
    åĪĨåī²
    0.08
    åĪĨæĪIJ
    0.08
    åĪĴåĪĨ
    0.08
     splits
    0.07
    à¹ģà¸ļà¹Īà¸ĩ
    0.07
    åĪĨ为
    0.07
     بÙĨدÛĮ
    0.07
     dividing
    0.07
    عاد
    0.07
    Activations Density 0.009%

    No Known Activations