© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42374
    Prev
    Next
    INDEX
    Explanations

    search interval refining

    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
    åĨ²å¤©
    -0.09
     translateY
    -0.08
    lator
    -0.08
    è£ľç¿Ĵ
    -0.08
     Lobby
    -0.07
    perator
    -0.07
     prép
    -0.07
    ontage
    -0.07
    à®®à¯Ī
    -0.07
     hub
    -0.07
    POSITIVE LOGITS
    缩å°ı
    0.08
     refinement
    0.08
     refining
    0.07
    继ç»Ńè¿Ľè¡Į
    0.07
    JI
    0.07
     narrowing
    0.07
    æĶ¶æķĽ
    0.07
     narrowed
    0.07
     Caval
    0.07
    /downloads
    0.07
    Activations Density 0.005%

    No Known Activations