© 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. 27431
    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
    du
    -0.07
     curve
    -0.07
    ä»ĸ们没æľī
    -0.06
    ueur
    -0.06
    oca
    -0.06
    èĮ¹
    -0.06
    å¸Ń
    -0.06
     Manny
    -0.06
    å¿łè¯ļ
    -0.06
     matter
    -0.06
    POSITIVE LOGITS
    icals
    0.08
    AINS
    0.08
    ĥĿ
    0.08
    olong
    0.08
    arth
    0.07
    Blank
    0.07
    rement
    0.07
    utters
    0.07
    utter
    0.07
    å§Ĩæĸ¯
    0.07
    Activations Density 0.000%

    No Known Activations