© 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. 55562
    Prev
    Next
    INDEX
    Explanations

    singularity, collapse, bang, fields

    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
    akis
    -0.08
    è´µåľ¨
    -0.08
     dicip
    -0.08
    ç«¥åŃIJ
    -0.08
    assen
    -0.07
    åı¤å±ĭ
    -0.07
    足äºĨ
    -0.07
    USART
    -0.07
     fortal
    -0.07
    ãģĭãģĴ
    -0.07
    POSITIVE LOGITS
     crumbling
    0.08
    çī©çIJĨ
    0.08
     physically
    0.07
     physical
    0.07
    physical
    0.07
    èĻļæĹł
    0.07
     brutal
    0.07
     rupture
    0.07
    çī©çIJĨåѦ
    0.07
    åĨ²çł´
    0.06
    Activations Density 0.003%

    No Known Activations