© 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. 12270
    Prev
    Next
    INDEX
    Explanations

    causal conjunctions (since, because)

    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·æľīå¾Ī好çļĦ
    -0.08
    ubile
    -0.08
    ],'
    -0.07
    禧
    -0.07
    æľīå¾Ī好çļĦ
    -0.07
    unami
    -0.07
    ÐŁÐ¾Ð´ÑĢоб
    -0.07
     ÙħجÙĩ
    -0.06
    mare
    -0.06
    éĻĪåħĪçĶŁ
    -0.06
    POSITIVE LOGITS
     otherwise
    0.12
    åIJ¦åĪĻ
    0.12
     Otherwise
    0.12
    ä¸įçĦ¶
    0.11
    otherwise
    0.11
    åIJ¦åĪĻä¼ļ
    0.10
    æīįèĥ½åľ¨
    0.10
    Otherwise
    0.10
    åIJ¦åīĩ
    0.10
    è¦ģä¸įçĦ¶
    0.10
    Activations Density 0.028%

    No Known Activations