© 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. 13657
    Prev
    Next
    INDEX
    Explanations

    adhered to

    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
     suce
    -0.08
    clave
    -0.08
    ijski
    -0.07
    ugins
    -0.07
    ига
    -0.07
    beauftrag
    -0.07
    джеÑĤ
    -0.07
    ÑĦиÑĨи
    -0.07
    HashTable
    -0.07
    identes
    -0.07
    POSITIVE LOGITS
     Desta
    0.08
    æľªå®Į
    0.07
    qn
    0.06
    หà¸Ļà¹īา
    0.06
    éļħ
    0.06
    ãĥĬãĤ¤
    0.06
    ta
    0.06
    akeup
    0.06
     Neste
    0.06
    auce
    0.06
    Activations Density 0.104%

    No Known Activations