© 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. 64850
    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
    ehr
    -0.07
    å¢Ł
    -0.06
    ohl
    -0.06
    仲
    -0.06
    ãģĬãģĭ
    -0.06
     Orn
    -0.06
    åŃIJæĽ°
    -0.06
    ulton
    -0.06
    éĶIJ
    -0.06
    诡
    -0.06
    POSITIVE LOGITS
    è¿Ľä¸ĢæŃ¥äºĨ解
    0.08
    åħ¶äºº
    0.07
     FAQ
    0.07
    èģĬä¸ĢèģĬ
    0.07
    nore
    0.07
    adx
    0.07
    éĺģä¸ĭ
    0.07
    æĤ£
    0.07
    认è¯ĨçļĦ
    0.07
    ä¿¡æģ¯ç§ijæĬĢæľīéĻIJåħ¬åı¸
    0.07
    Activations Density 0.000%

    No Known Activations