© 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. 3272
    Prev
    Next
    INDEX
    Explanations

    . instance

    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
    åħ¶ä¸ŃæľĢ
    -0.07
    æľĢ
    -0.07
    enet
    -0.07
    è¾Ļ
    -0.07
     unh
    -0.06
    æ²»
    -0.06
    å¼Ģ
    -0.06
     safest
    -0.06
    æľīåĪ©
    -0.06
    è¿Ļ
    -0.06
    POSITIVE LOGITS
    çŃīåħ¶ä»ĸ
    0.09
    æĬĺä¸įæī£
    0.08
    ä»»ä½ķåħ¶ä»ĸ
    0.08
     bowiem
    0.08
    å¥¢æľĽ
    0.08
    æľīåħ¶ä»ĸ
    0.08
    ×£
    0.08
    ëģ¼
    0.08
    ä¹ĭèĻķ
    0.08
    è§Ħå®ļçļĦåħ¶ä»ĸ
    0.07
    Activations Density 0.004%

    No Known Activations