© 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. 16805
    Prev
    Next
    INDEX
    Explanations

    heterogeneity or characteristic

    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
    å±ĬæŶ
    -0.08
    æĤ¨çļĦä½įç½®
    -0.08
    æѤæĻĤ
    -0.07
     chances
    -0.07
    æѤæŶ
    -0.07
    å°Ĩåĩºçİ°
    -0.07
    æľīåı¯èĥ½æĺ¯
    -0.07
    нÑı
    -0.07
    unlikely
    -0.07
     créd
    -0.07
    POSITIVE LOGITS
    çī¹æĢ§
    0.12
    çŃīçī¹çĤ¹
    0.11
    çī¹çĤ¹
    0.11
    çī¹æĢ§çļĦ
    0.11
    çļĦçī¹çĤ¹
    0.10
    çļĦçī¹æĢ§
    0.10
    åĽºæľīçļĦ
    0.10
    æŃ£åĽłä¸º
    0.10
     inherent
    0.10
     nature
    0.10
    Activations Density 0.125%

    No Known Activations