© 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. 18793
    Prev
    Next
    INDEX
    Explanations

    luck and chance

    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
    æ°¸ä¸į
    -0.05
    rata
    -0.05
    人æĦı
    -0.05
    ripple
    -0.05
    9
    -0.05
    ä¸ĢçĽ´åľ¨
    -0.05
    Feedback
    -0.05
    nt
    -0.05
    å¤
    -0.05
     feedback
    -0.05
    POSITIVE LOGITS
    ilat
    0.07
    ä¹ĭéķ¿
    0.06
    cox
    0.06
    顺
    0.06
    ุษ
    0.06
     nasib
    0.06
    ,json
    0.06
    ueil
    0.06
    maÃŁnahmen
    0.06
    ilé
    0.06
    Activations Density 0.014%

    No Known Activations