© 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. 17774
    Prev
    Next
    INDEX
    Explanations

    quark, anti-quark,meson, or top

    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
    umer
    -0.07
     cited
    -0.06
    unders
    -0.06
    èģĶå¸Ń
    -0.06
     Cyber
    -0.06
    åĽ´ç»ķçĿĢ
    -0.06
    æľīä¸Ģ次
    -0.05
    å¹ħ
    -0.05
    -0.05
    mites
    -0.05
    POSITIVE LOGITS
    pire
    0.09
    گاÙĩ
    0.09
    éroport
    0.08
    ÑģовеÑģÑĤ
    0.08
    essar
    0.08
    笤
    0.08
    uson
    0.08
    stantiate
    0.08
    nhof
    0.08
    ÏĦοÏĢοι
    0.08
    Activations Density 0.001%

    No Known Activations