© 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. 40377
    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
     impuls
    -0.07
    marshall
    -0.07
     heck
    -0.07
     sÃŃ
    -0.07
    _listen
    -0.07
    arse
    -0.07
    Pixels
    -0.07
    ippo
    -0.06
    stu
    -0.06
     thereof
    -0.06
    POSITIVE LOGITS
    ä¸įäºĨå¤ļä¹ħ
    0.07
    å¦ĤæŀľéľĢè¦ģ
    0.06
    alian
    0.06
    å¦Ĥæŀľåıijçİ°
    0.06
    ä¸įä¹ħçļĦ
    0.06
    tung
    0.06
    å¦Ĥæŀľæľī
    0.06
    ä¿ł
    0.06
     Paren
    0.06
     leo
    0.06
    Activations Density 0.000%

    No Known Activations