© 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. 28389
    Prev
    Next
    INDEX
    Explanations

    causes or effects

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    éĥ½èĥ½å¤Ł
    -0.08
    ãģĭãĤĤãģĹãĤĮãģ¾ãģĽãĤĵãģĮ
    -0.08
    она
    -0.08
    åľ¨åĨħçļĦ
    -0.07
    åıĪä¸įæĺ¯
    -0.07
    ãģ¨è¨ĢãĤıãĤĮãĤĭ
    -0.07
     degusta
    -0.07
     anyways
    -0.07
    .eql
    -0.07
    )&&
    -0.07
    POSITIVE LOGITS
     Ø£Ùħر
    0.07
     helps
    0.07
    help
    0.07
    以åıĬåľ¨
    0.07
    å°±æĺ¯è¿Ļ个
    0.07
    wyn
    0.06
     validates
    0.06
    ä¸įæĹ©
    0.06
     ensures
    0.06
    ëĮĢëĬĶ
    0.06
    Activations Density 0.461%

    No Known Activations