© 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. 39036
    Prev
    Next
    INDEX
    Explanations

    purity and contaminants

    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
    éen
    -0.07
    ież
    -0.07
    åħĭåĬĽ
    -0.07
    igid
    -0.07
    implemented
    -0.06
    çĽĪçĽĪ
    -0.06
    æģ¤
    -0.06
    ÙħÙĪد
    -0.06
    æĢİä¹Īèµ°
    -0.06
    ä¹°èıľ
    -0.06
    POSITIVE LOGITS
     purity
    0.13
    æĿĤè´¨
    0.12
    纯åĩĢ
    0.12
    纯度
    0.11
    纯æ´ģ
    0.11
     contaminants
    0.11
     contamination
    0.11
     cleanliness
    0.10
     lẫn
    0.09
     composition
    0.09
    Activations Density 0.085%

    No Known Activations