© 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. 13440
    Prev
    Next
    INDEX
    Explanations

    code definition 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
    acle
    -0.07
     lave
    -0.07
    ÙĨÛĮÙĨ
    -0.07
    פ׾
    -0.06
    enville
    -0.06
     référenc
    -0.06
    paralle
    -0.06
    .tail
    -0.06
    EIC
    -0.06
     zeroes
    -0.06
    POSITIVE LOGITS
    ostr
    0.07
    åĪ©äºļ
    0.07
    ORIZ
    0.07
    èĩªå¸¦çļĦ
    0.07
    oret
    0.07
     resmi
    0.07
    ä¼¯æł¼
    0.07
     Libert
    0.07
    å§Ĺ
    0.07
    æ®ĩ
    0.07
    Activations Density 1.039%

    No Known Activations