© 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. 15550
    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
    å«£çĦ¶
    -0.08
    ç½²
    -0.07
    biz
    -0.07
    वान
    -0.07
    å°Ĩä»ĸ们
    -0.07
    basis
    -0.07
    обоÑĢоÑĤ
    -0.07
    aje
    -0.07
    à¸ģะ
    -0.07
    orgen
    -0.07
    POSITIVE LOGITS
    iels
    0.07
    åŀĤ
    0.07
     unf
    0.06
    ä¸Ģåĩº
    0.06
    å©
    0.06
    å¯Įæľī
    0.06
    å¹¢
    0.06
    IMER
    0.06
    illen
    0.06
    imos
    0.06
    Activations Density 0.000%

    No Known Activations