© 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. 28743
    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
    æľ¬å¹´
    -0.07
    anska
    -0.07
    æľīéĻIJ责任
    -0.07
    anic
    -0.07
    kä
    -0.07
    onta
    -0.06
    ont
    -0.06
    çŁŃ
    -0.06
    å¾Ĺè¿ĩ
    -0.06
     trách
    -0.06
    POSITIVE LOGITS
    åĪ©çĶ¨å¥½
    0.08
    ilty
    0.07
    Che
    0.07
    Vars
    0.07
    缸åħ³éĺħ读
    0.07
    ÏĥηÏĤ
    0.07
    sph
    0.07
    ãĥªãĥ¼ãĥł
    0.07
    æĢ»ä¼ļæľī
    0.07
    ONGL
    0.06
    Activations Density 0.000%

    No Known Activations