© 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. 12659
    Prev
    Next
    INDEX
    Explanations

    mathematical proofs or code syntax

    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
    æłijä¸Ģ
    -0.08
    ude
    -0.07
    ink
    -0.07
    çģ¿
    -0.07
    èĤ¥
    -0.07
    åĨł
    -0.07
    /o
    -0.07
    Ùĩب
    -0.07
    å®īæ£Ģ
    -0.06
     ci
    -0.06
    POSITIVE LOGITS
     decis
    0.07
    ëģĶ
    0.07
    allis
    0.07
    adalafil
    0.07
    evin
    0.07
    anja
    0.07
    å¹³åĿĩæ¯ı
    0.07
    tran
    0.06
    ativa
    0.06
     conclus
    0.06
    Activations Density 0.001%

    No Known Activations