© 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. 48940
    Prev
    Next
    INDEX
    Explanations

    familiar source of inspiration

    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
     ourselves
    -0.08
    atron
    -0.08
    å°ıåŃIJ
    -0.07
    etch
    -0.07
    ppard
    -0.07
    onis
    -0.07
    ahui
    -0.07
     ìŀĪëĬĶëį°ìļĶ
    -0.07
    emann
    -0.07
    æŃ£ç¡®è®¤è¯Ĩ
    -0.07
    POSITIVE LOGITS
    ãģĵãĤĮãĤĤ
    0.10
    è¿ĻæŶçļĦ
    0.08
     here
    0.07
    ·
    0.07
    ä¹ħä¹ĭ
    0.07
    ´
    0.07
    éģ¨
    0.07
    à¤ļà¥įà¤ļ
    0.07
    ieder
    0.06
    èĤ²
    0.06
    Activations Density 0.032%

    No Known Activations