© 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. 56728
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    .shtml
    -0.08
    ãģļ
    -0.07
    ile
    -0.07
    婺
    -0.07
    彬
    -0.07
    ists
    -0.06
    culus
    -0.06
     sottos
    -0.06
     equ
    -0.06
     Kla
    -0.06
    POSITIVE LOGITS
    iak
    0.08
    agé
    0.07
    اÙĦات
    0.07
    å¤Ħ女
    0.07
    usul
    0.07
    δεÏĤ
    0.07
    çŀİ
    0.07
    Counter
    0.07
     Penj
    0.07
    æĭįæīĭ
    0.06
    Activations Density 0.000%

    No Known Activations