© 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. 9282
    Prev
    Next
    INDEX
    Explanations

    between or relation

    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
    伯伯
    -0.08
    uari
    -0.08
    scribe
    -0.07
    amenta
    -0.07
    saan
    -0.07
     tournée
    -0.07
    ento
    -0.06
    urop
    -0.06
    vasti
    -0.06
    gres
    -0.06
    POSITIVE LOGITS
     between
    0.20
    between
    0.19
     междÑĥ
    0.17
     zwischen
    0.16
    -between
    0.16
     giữa
    0.16
     Between
    0.16
    ระหวà¹Īาà¸ĩ
    0.14
     بÙĬÙĨ
    0.14
     BETWEEN
    0.14
    Activations Density 0.290%

    No Known Activations