© 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. 13958
    Prev
    Next
    INDEX
    Explanations

    heat equation

    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
    rips
    -0.08
    æłijä¸Ĭ
    -0.08
    æĨ¬
    -0.08
     valg
    -0.07
    æłijä¸ĬçļĦ
    -0.07
    кÑĥпа
    -0.07
    éģĵæĿ¥
    -0.07
    semb
    -0.07
    ordat
    -0.07
     Futbol
    -0.07
    POSITIVE LOGITS
    çĥ§
    0.09
     Burn
    0.07
    çģ¼
    0.07
     blazing
    0.07
    èı²
    0.07
    çĥ§ä¼¤
    0.07
    漫
    0.07
    积åĪĨ
    0.07
    NSE
    0.06
     burnt
    0.06
    Activations Density 0.002%

    No Known Activations