© 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. 57076
    Prev
    Next
    INDEX
    Explanations

    standard or typical followed by a descriptor

    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
    äºĨ对
    -0.10
    ÑģÑı
    -0.09
    nant
    -0.09
    nge
    -0.09
    oz
    -0.09
    ality
    -0.08
    ãĤĭ
    -0.08
    تÛĮ
    -0.08
    anager
    -0.08
    اÛģ
    -0.08
    POSITIVE LOGITS
    i
    0.09
    0.08
    çļĦçŃĶæ¡Ī
    0.08
    çļĦèĬ±
    0.07
    edList
    0.07
    icians
    0.07
    ิà¹Īà¸ĩ
    0.06
    erweise
    0.06
    ician
    0.06
    åŁºå°¼
    0.06
    Activations Density 0.001%

    No Known Activations