© 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. 49496
    Prev
    Next
    INDEX
    Explanations

    salvation and Savior

    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
    çļĦ大åŀĭ
    -0.06
    ziem
    -0.06
     respet
    -0.06
    rompt
    -0.06
    大åŀĭ
    -0.06
     cref
    -0.06
    jol
    -0.06
    ải
    -0.06
    樽
    -0.06
    iya
    -0.06
    POSITIVE LOGITS
     salvation
    0.08
     unconditional
    0.08
     ÑģпаÑģа
    0.08
    æķijèµİ
    0.08
    æĭ¯æķij
    0.08
    æĶ¹åıĺèĩªå·±
    0.08
     saving
    0.07
     избав
    0.07
    ç»Ķ
    0.07
    转移
    0.07
    Activations Density 0.023%

    No Known Activations