© 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. 19768
    Prev
    Next
    INDEX
    Explanations

    career and life decisions

    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
    yra
    -0.06
    มาà¸ķรà¸IJาà¸Ļ
    -0.06
    使çĶ¨ä¸Ń
    -0.06
     reception
    -0.06
    exo
    -0.06
    ouw
    -0.06
     rece
    -0.06
    æłĩåĩĨçļĦ
    -0.05
     standar
    -0.05
    ä¼ļ使çĶ¨
    -0.05
    POSITIVE LOGITS
    å¼ķ导
    0.07
    ©
    0.06
    è½´
    0.06
    fahrt
    0.06
    èĪŁ
    0.05
     ambiguous
    0.05
    åīĤåĴĮ
    0.05
    æĮĩæĺİäºĨ
    0.05
    tent
    0.05
    åıĤè°ĭ
    0.05
    Activations Density 0.021%

    No Known Activations