© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16172
    Prev
    Next
    INDEX
    Explanations

    absence of something

    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
    æ²®
    -0.06
    ìĸ¸
    -0.06
    ND
    -0.06
    olen
    -0.06
    éľŀ
    -0.06
    pun
    -0.06
    ÙĪدÙĬ
    -0.06
     Andr
    -0.06
     pula
    -0.06
    éľĸ
    -0.06
    POSITIVE LOGITS
     вовÑģе
    0.11
    æł¹æľ¬ä¸į
    0.11
     altogether
    0.10
     вообÑīе
    0.09
    æł¹æľ¬å°±ä¸į
    0.09
    ä»Ģä¹Īéĥ½æ²¡æľī
    0.08
    inkin
    0.08
    æł¹æľ¬æ²¡
    0.08
     überhaupt
    0.08
    ascript
    0.08
    Activations Density 0.087%

    No Known Activations