© 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. 10065
    Prev
    Next
    INDEX
    Explanations

    full throttle burst

    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
    æŁĶåĴĮ
    -0.10
    Soft
    -0.10
    温å©ī
    -0.10
    温馨çļĦ
    -0.09
    Slow
    -0.09
    åĴĮè°IJ
    -0.09
     gracefully
    -0.09
    温润
    -0.09
    æħ¢
    -0.08
    æ·¡éĽħ
    -0.08
    POSITIVE LOGITS
     aggressive
    0.16
    çĭĤéĩİ
    0.13
     агÑĢеÑģÑģив
    0.12
    强æĤį
    0.12
    çĥĪ
    0.12
    åĪºæ¿ĢæĢ§
    0.12
    çĮĽçĥĪ
    0.12
    æ¿ĢçĥĪ
    0.11
     aggressively
    0.11
    çĥĪçļĦ
    0.11
    Activations Density 0.801%

    No Known Activations