© 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. 24662
    Prev
    Next
    INDEX
    Explanations

    align and alignment

    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
    iley
    -0.09
    ulent
    -0.08
    Ñĩина
    -0.07
    خاÙĨÙĩ
    -0.07
    边形
    -0.07
    anyol
    -0.07
    entially
    -0.07
    iable
    -0.07
    rena
    -0.07
    aring
    -0.07
    POSITIVE LOGITS
    edList
    0.09
    (li
    0.08
    ments
    0.08
    =center
    0.08
    äºĨ对
    0.08
    ç§ĭæľĪ
    0.08
    encontre
    0.08
     Diri
    0.08
    inser
    0.07
    uffici
    0.07
    Activations Density 0.024%

    No Known Activations