© 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. 47620
    Prev
    Next
    INDEX
    Explanations

    consolidated empire rulers

    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
    缸æĴŀ
    -0.07
     mamma
    -0.06
     browsing
    -0.06
    æ²³åİ¿
    -0.06
    éĵ®
    -0.06
     abat
    -0.06
     sampling
    -0.06
    æĶ¯æŀ¶
    -0.06
    angel
    -0.06
    uer
    -0.06
    POSITIVE LOGITS
    ç¨³åĽº
    0.11
    å·©åĽº
    0.11
     stabil
    0.10
     consolid
    0.10
    åĩºåħµ
    0.10
     consolidated
    0.10
     consolidation
    0.10
    æĿ¯éħĴ
    0.10
     military
    0.09
    æī©å»º
    0.09
    Activations Density 0.044%

    No Known Activations