© 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. 48836
    Prev
    Next
    INDEX
    Explanations

    alternatives or possibilities

    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
     either
    -0.10
    either
    -0.10
    è¦ģä¹Ī
    -0.10
     totiž
    -0.09
    è¦ģä¹Īæĺ¯
    -0.09
    æĪĸ以
    -0.09
     EITHER
    -0.08
     Ø¥Ùħا
    -0.08
    æĪĸåĽł
    -0.08
     ugyanis
    -0.08
    POSITIVE LOGITS
    æł¹æľ¬å°±æĺ¯
    0.12
     sebaliknya
    0.12
    æľīåħ¶ä»ĸ
    0.10
    å¹²èĦĨ
    0.10
    æľ¬èº«å°±æĺ¯
    0.10
     вовÑģе
    0.08
    æł¹æľ¬å°±
    0.08
     simply
    0.08
     simplement
    0.08
     наобоÑĢоÑĤ
    0.08
    Activations Density 0.057%

    No Known Activations