© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19031
    Prev
    Next
    INDEX
    Explanations

    employee turnover and retention

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ikir
    -0.06
    oles
    -0.06
    ÙĨÙĬÙģ
    -0.05
    æĹłå®³
    -0.05
    æ¯įåŃIJ
    -0.05
    åıĸç¼Ķ
    -0.05
    KG
    -0.05
    rophy
    -0.05
     won
    -0.05
    elic
    -0.05
    POSITIVE LOGITS
    holt
    0.06
    æĭ¼
    0.06
    iais
    0.06
     heated
    0.06
    æ¹
    0.05
    çĥŃçĤ¹éĹ®é¢ĺ
    0.05
    åĽ°éļ¾
    0.05
    attr
    0.05
    back
    0.05
    boats
    0.05
    Activations Density 0.028%

    No Known Activations