© 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. 23866
    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
    åĦŁ
    -0.07
    em
    -0.06
    eer
    -0.06
    ry
    -0.06
    তà§ĭ
    -0.06
    outs
    -0.06
     Lans
    -0.06
    .headers
    -0.06
    æ¯į
    -0.06
    说äºĨç®Ĺ
    -0.06
    POSITIVE LOGITS
    ä¹ĭè¨Ģ
    0.09
    ä¹ĭéŁ³
    0.08
    ä¹ĭæĦŁ
    0.08
    ä¼ģä¸ļæŁ¥è¯¢
    0.08
    HTTPRequest
    0.07
    ä¹ĭæĥħ
    0.07
    ä¹ĭåIJį
    0.07
     fruc
    0.07
    .kr
    0.07
    jukan
    0.07
    Activations Density 0.000%

    No Known Activations