© 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. 55456
    Prev
    Next
    INDEX
    Explanations

    proposed mechanism

    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
    igi
    -0.07
    ildo
    -0.07
    aglia
    -0.07
    èµ°ä¸Ģèµ°
    -0.07
    çĽ²
    -0.07
     determin
    -0.07
    orme
    -0.07
    iscal
    -0.07
    æĹ¥ä»¥æĿ¥
    -0.07
    isc
    -0.07
    POSITIVE LOGITS
     mechanism
    0.08
    æľºåĪ¶
    0.07
     Proposed
    0.07
    æľºçIJĨ
    0.07
     Mechan
    0.07
    仲
    0.07
     attacking
    0.07
     ÑģÑĤад
    0.07
     proposed
    0.07
     intermedi
    0.07
    Activations Density 0.009%

    No Known Activations