© 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. 3315
    Prev
    Next
    INDEX
    Explanations

    specific detail

    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
    åŁºæľ¬åİŁçIJĨ
    -0.08
    顺便
    -0.08
     essentially
    -0.08
    æľ¬æĿ¥å°±
    -0.08
    ç´¢æĢ§
    -0.08
     ÑģооÑĤвеÑĤÑģÑĤвенно
    -0.08
     вообÑīе
    -0.08
    åIJĮ樣
    -0.08
     stessi
    -0.08
    æĢ»ä½ĵè¦ģæ±Ĥ
    -0.08
    POSITIVE LOGITS
     specific
    0.10
    çī¹å®ļçļĦ
    0.10
     Specific
    0.10
     spesifik
    0.09
    à¹Ģà¸Īาะ
    0.09
    åħ·ä½ĵçļĦ
    0.09
    /detail
    0.09
    åħ·ä½ĵåĪĨæŀIJ
    0.09
    åħ·ä½ĵ
    0.09
    pecific
    0.09
    Activations Density 0.133%

    No Known Activations