© 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. 39920
    Prev
    Next
    INDEX
    Explanations

    clever way

    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
    weiler
    -0.09
    inach
    -0.08
    owler
    -0.08
    اÙĪر
    -0.08
     Sanders
    -0.07
    ubre
    -0.07
    ORA
    -0.07
    -picture
    -0.07
    witch
    -0.07
    ishop
    -0.07
    POSITIVE LOGITS
    å·§å¦ĻçļĦ
    0.10
    å·§å¦Ļ
    0.10
    çĤ¹åŃIJ
    0.10
     léo
    0.10
    å·§
    0.10
    ä¹ĭå¤Ħåľ¨äºİ
    0.09
    å¦Ļ
    0.09
    ç»Ŀ伦
    0.09
     combination
    0.09
    å·§å¦Ļåľ°
    0.08
    Activations Density 0.024%

    No Known Activations