© 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. 33446
    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
    È
    -0.07
    羣æŃ£çļĦ
    -0.06
    okit
    -0.06
    å®ļ
    -0.06
    å®Ĺ
    -0.06
     ketentuan
    -0.06
    对åIJ§
    -0.06
    ting
    -0.06
    pector
    -0.05
    ina
    -0.05
    POSITIVE LOGITS
    sembles
    0.08
    åħ¶ä»ĸ人çļĦ
    0.08
    namen
    0.08
    metter
    0.08
    arque
    0.08
     Karn
    0.08
    #echo
    0.07
    管çIJĨæīĢ
    0.07
    鼷æĸ¯
    0.07
    éĺħ读åħ¨æĸĩ
    0.07
    Activations Density 0.000%

    No Known Activations